CN109298136A - Air Quality Evaluation method, apparatus, equipment and storage medium - Google Patents
Air Quality Evaluation method, apparatus, equipment and storage medium Download PDFInfo
- Publication number
- CN109298136A CN109298136A CN201811183512.0A CN201811183512A CN109298136A CN 109298136 A CN109298136 A CN 109298136A CN 201811183512 A CN201811183512 A CN 201811183512A CN 109298136 A CN109298136 A CN 109298136A
- Authority
- CN
- China
- Prior art keywords
- air quality
- meteorologic factor
- pollutant
- specified
- time section
- 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
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 55
- 238000012544 monitoring process Methods 0.000 claims abstract description 240
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 94
- 231100000719 pollutant Toxicity 0.000 claims abstract description 94
- 238000000611 regression analysis Methods 0.000 claims abstract description 20
- 230000006870 function Effects 0.000 claims description 61
- 238000003915 air pollution Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 239000000809 air pollutant Substances 0.000 claims description 6
- 231100001243 air pollutant Toxicity 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000008901 benefit Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000009792 diffusion process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- 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 or the display, e.g. intermittent measurement or digital display
-
- 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
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0031—General constructional details of gas analysers, e.g. portable test equipment concerning the detector comprising two or more sensors, e.g. a sensor array
- G01N33/0034—General constructional details of gas analysers, e.g. portable test equipment concerning the detector comprising two or more sensors, e.g. a sensor array comprising neural networks or related mathematical techniques
-
- 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 or the display, e.g. intermittent measurement or digital display
- G01N33/0068—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display using a computer specifically programmed
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Biochemistry (AREA)
- Combustion & Propulsion (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Air Quality Evaluation method, apparatus, equipment and storage mediums.This method comprises: the historical data of pollutant data and meteorologic factor based on monitoring determines the regression relation of pollutant and meteorologic factor using regression analysis；Benchmark meteorological field is constructed using the historical data of meteorologic factor, benchmark meteorological field is used to describe the meteorologic factor in the distribution of the baseline probability of specified monitoring region and specified monitoring time section；Using the regression relation of pollutant and meteorologic factor, pollutant under calculating benchmark meteorological field, to evaluate air quality.Air Quality Evaluation method, apparatus, equipment and the storage medium provided according to embodiments of the present invention can objectively reflect that actual air quality, Air Quality Evaluation result are more accurate.
Description
Technical field
The present invention relates to environmental monitoring field more particularly to a kind of Air Quality Evaluation method, apparatus, equipment and storage to be situated between
Matter.
Background technique
With the quickening of rapid economic development and urbanization process, the energy largely consumes and disposal of pollutants is significantly increased,
Leading to air quality problems, the situation is tense, and lasting high density air pollution takes place frequently, seriously threaten people health and
Ecological safety.Since the concentration of atmosphere pollution is needed for the regulatory requirement of atmosphere pollution to sky by the interference of meteorologic factor
Makings amount carries out objective and accurate assessment.
Currently, air quality appraisal procedure is usually to the atmosphere pollution real-time monitored by hour concentration data, into
The simple arithmetic average of row, so that it is determined that atmosphere pollution mean annual concentration.However, interference of the air quality by meteorologic factor
It is very big, in the prior art the simple arithmetic average of the pollutant data to evaluation do not have the time and spatially can
Than property, the actual mass of air cannot be objectively responded.
Summary of the invention
Air Quality Evaluation method, apparatus, equipment and the storage medium provided according to embodiments of the present invention realizes that atmosphere is dirty
The concentration of dye object is comparable over time and space, objectively to reflect actual air quality.
One side according to an embodiment of the present invention provides a kind of Air Quality Evaluation method, the Air Quality Evaluation method
Include:
The historical data of pollutant data and meteorologic factor based on monitoring is determined using regression analysis
The regression relation of pollutant and meteorologic factor；
Benchmark meteorological field is constructed using the historical data of meteorologic factor, benchmark meteorological field is for describing meteorologic factor specified
Monitor the baseline probability distribution of region and specified monitoring time section；
Using the regression relation of pollutant and meteorologic factor, the atmosphere pollution under calculating benchmark meteorological field is dense
Degree, to evaluate air quality.
According to another aspect of an embodiment of the present invention, a kind of Air Quality Evaluation device, Air Quality Evaluation dress are provided
It sets and includes:
Regression relation determining module, the history number for pollutant data based on monitoring and meteorologic factor
According to determining the regression relation of pollutant and meteorologic factor using regression analysis；
Benchmark meteorological field construct module, for using meteorologic factor historical data construct benchmark meteorological field, reference gas as
Field is for describing meteorologic factor in the distribution of the baseline probability of specified monitoring region and specified monitoring time section；
Pollutant computing module, for the regression relation using pollutant and meteorologic factor, meter
The pollutant under benchmark meteorological field is calculated, to evaluate air quality.
It is according to an embodiment of the present invention in another aspect, providing a kind of Air Quality Evaluation equipment, which sets
Standby includes: processor and the memory for being stored with computer program instructions；
Processor realizes the method such as Air Quality Evaluation provided in an embodiment of the present invention when executing computer program instructions.
It is according to an embodiment of the present invention in another aspect, a kind of computer storage medium is provided, in the computer storage medium
Computer program instructions are stored with, such as air provided in an embodiment of the present invention is realized when computer program instructions are executed by processor
The method of quality evaluation.
Air Quality Evaluation method, apparatus, equipment and storage medium provided in an embodiment of the present invention, are primarily based on monitoring
The historical data of pollutant data and meteorologic factor determines air pollution concentration and meteorology in conjunction with regression analysis
Then the regression relation of factor constructs benchmark meteorological field using the historical data of meteorologic factor, recycles the regression relation, calculate
Air pollution concentration under benchmark meteorological field realizes that the concentration of atmosphere pollution is comparable over time and space, with visitor
It sees ground and reflects actual air quality.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, will make below to required in the embodiment of the present invention
Attached drawing is briefly described, for those of ordinary skill in the art, without creative efforts, also
Other drawings may be obtained according to these drawings without any creative labor.
Fig. 1 shows the flow diagram of the Air Quality Evaluation method of one embodiment of the invention offer；
Fig. 2 shows the structural schematic diagrams for the Air Quality Evaluation device that one embodiment of the invention provides；
Fig. 3 shows the hardware structural diagram of the Air Quality Evaluation equipment of one embodiment of the invention offer.
Specific embodiment
The feature and exemplary embodiment of various aspects of the invention is described more fully below, in order to make mesh of the invention
, technical solution and advantage be more clearly understood, with reference to the accompanying drawings and embodiments, the present invention is further retouched in detail
It states.It should be understood that specific embodiment described herein is only configured to explain the present invention, it is not configured as limiting the present invention.
To those skilled in the art, the present invention can be real in the case where not needing some details in these details
It applies.Below the description of embodiment is used for the purpose of better understanding the present invention to provide by showing example of the invention.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence " including ... ", it is not excluded that including
There is also other identical elements in the process, method, article or equipment of element.
The concentration of the atmosphere pollution real-time monitored at present the influence that not only contaminated object discharges, also by meteorologic factor
Influence, such as: the meteorologic factors such as temperature, air pressure, wind speed and direction.However the basic reason of atmosphere pollution is caused to be serious
Pollutant emission, just because of the influence of meteorologic factor, therefore the concentration of the atmosphere pollution of a certain region of real-time monitoring is simultaneously
It cannot reflect the true pollutant discharge amount of the region.
As an example, first city is located at seashore, and second city is located at flat-bottomed land, and the atmosphere dirt that first city is annual
It contaminates object discharge amount and is greater than the annual Air Pollutants Emissions in second city.But since first city is located at seashore, first city
Meteorological condition be convenient for the diffusion of atmosphere pollution, and since second city is located at flat-bottomed land, and the atmosphere pollution in second city
It is not easy to spread.Formally due to the influence of meteorologic factor, cause the concentration of the atmosphere pollution in the first city of monitoring lower than second city
Atmosphere pollution concentration, cause the concentration of the atmosphere pollution of monitoring that cannot really reflect the discharge feelings of atmosphere pollution
Condition, the accuracy rate in turn resulting in Air Quality Evaluation are low.Therefore, it when evaluating air quality, needs in time and sky
Between upper removal meteorologic factor influence, the Air Pollutant Emission situation of each department is truly reacted, so that various regions region measurement
Pollutant has comparability over time and space.
Based on this, the embodiment of the present invention proposes a kind of Air Quality Evaluation method, apparatus, equipment and storage medium, is based on
The pollutant data of monitoring and the historical data of meteorologic factor establish time of pollutant and meteorologic factor
Return relationship；And using the building of the historical data of meteorologic factor for describing meteorologic factor at specified monitoring region and specified monitoring
Between section baseline probability distribution benchmark meteorological field；Using the regression relation of pollutant and meteorologic factor, base is calculated
Pollutant under quasi- meteorological field is realized with removing influence of the meteorologic factor to pollutant to air matter
Amount is accurately evaluated.
Air Quality Evaluation method provided in an embodiment of the present invention is described in detail in conjunction with attached drawing first below.Fig. 1
The flow diagram of the Air Quality Evaluation method 100 provided according to embodiments of the present invention is shown.As shown in Figure 1, the present invention is real
Apply example provide in Air Quality Evaluation method the following steps are included:
S110, the historical data of pollutant data and meteorologic factor based on monitoring, using regression analysis,
Determine the regression relation of pollutant and meteorologic factor.
In an embodiment of the present invention, due to the influence of meteorologic factor, the concentration of the atmosphere pollution of monitoring can not be anti-
Answer the discharge amount of true atmosphere pollution, it is therefore desirable to establish the concentration of the atmosphere pollution of monitoring and reacting for meteorologic factor
Relationship, to determine influence of the meteorologic factor to air pollution concentration.And establish atmosphere pollution concentration and meteorologic factor it is anti-
It should be related to, then need to obtain the historical data of meteorologic factor and the concentration of atmosphere pollution corresponding with meteorologic factor.
In an embodiment of the present invention, step S110 the following steps are included:
S1101, obtain air quality monitoring point in specified monitoring region the corresponding meteorology of specified monitoring time section because
The historical data of element.
In an embodiment of the present invention, for air quality monitoring point the meteorologic factor of specified monitoring time section history
Data are the meteorological datas acquired in the corresponding meteorological site of air quality monitoring point.As an example, air quality
The corresponding meteorological site in monitoring point can be the meteorological site nearest apart from the air quality monitoring point.For in each monitoring region
The historical data of meteorologic factor of meteorological site can be obtained from national weather data network.For the history of meteorologic factor
The acquisition of data can be chosen according to the demand of Air Quality Evaluation.
As an example, if the corresponding meteorological site of air quality monitoring point is the A meteorological site of Beijing, prison is specified
The January for surveying the A meteorological site that the period is Beijing in 2012, then need to obtain Beijing's A meteorological site in January, 2012
The historical data of the meteorologic factor of part.
S1102, using regression analysis, by air quality monitoring point in the pollutant for specifying monitoring time section
It is expressed as the regression function indicated by air quality monitoring point in the corresponding meteorologic factor of specified monitoring time section, by returning letter
Number determines the regression relation of pollutant and meteorologic factor.
In an embodiment of the present invention, the data of the pollutant of each air quality monitoring point can be from environment
Monitoring master station is obtained.
Wherein, regression analysis refers to determining one kind of complementary quantitative relationship between two or more variable
Statistical analysis technique.Therefore regression analysis is utilized in embodiments of the present invention, discloses pollutant and meteorologic factor
Reaction relation.
Regression analysis includes non parametric regression, and non parametric regression is utilized in the case where the form of regression function is unknown
One group of given data (xk, yk), the value of estimation dependent variable y is gone to specified independent variable x value.Wherein, k=1,2 ... ..n, n are
Positive integer.Any a priori assumption due to distribution-free regression procedure independent of data, the formal freedom of regression function in nonparametric regression model,
Therefore flexibility and adaptability are enhanced.
Therefore the embodiment of the present invention can be using time of non parametric regression algorithm building air pollution concentration and meteorologic factor
Return relationship, wherein air pollution concentration and the regression relation of meteorologic factor can use following expression formula and be indicated:
yt(s)=m (xt(s), s)+εt(s) (1)
Wherein, s is specified air quality monitoring point, ytIt (s) is in specified air quality monitoring point in specified monitoring
The pollutant acquired in period.As an example, specified air quality monitoring point is the B air of Beijing
Quality-monitoring point, yt(s) then dense for atmosphere pollution of the B air quality monitoring o'clock in t hours of 1 year jth season
Degree, wherein i, j and t are positive integer, and the value range of t is 1 to k, and k is the positive integer greater than 1.
xtIt (s) is specified air quality monitoring point in the corresponding meteorologic factor of specified monitoring time section.As an example,
xtIt (s) is t hour corresponding meteorologic factors of the B air quality monitoring o'clock 1 year jth season.Wherein, meteorologic factor is extremely
It less include any one of following item: temperature T, air pressure P, wind direction W and wind speed V.
As a specific example, xtIt (s) is the vector comprising at least one meteorologic factor, i.e. xt(s)=(Tt,Pt,Wt,
Vt), TtFor the t hours corresponding temperature in 1 year jth season, PtFor the t hours corresponding gas in 1 year jth season
Pressure, WtThe t hours corresponding wind directions in 1 year jth season, VtFor the t hours corresponding wind speed in 1 year jth season.
Since the form of the recurrence receptance function in distribution-free regression procedure is not fixed, it is therefore desirable to according to the atmosphere of monitoring
The historical data of pollutant concentration data and meteorologic factor carries out estimation and returns receptance function.Distribution-free regression procedure includes that core returns
Return, local polynomial regression and neighbour return etc. a variety of homing methods.
Although the origin of different distribution-free regression procedures is different, it can will return receptance function and be considered as about yt
(s) linear combination.That is, returning the estimation of receptance function m (x, s)Can use following expression formula into
Row indicates:
Wherein, Wt(x, s) is known as weight function.Weight function plays smooth interaction in estimating recurrence receptance function, with
Eliminate the enchancement factor of disturbance.
As an example, estimated using the N-W kernel function estimation method in kernel regression to receptance function m (x) is returned
Meter.N-W kernel estimates are a kind of weighted average estimations, and kernel function K () is a weight function.Wherein, Wt(x) it can use core
The historical data x of function K (), meteorologic factort(s) it is calculated with smoothing parameter h.As a specific example, kernel function can
Think K (u)=(2 π)-1/2exp(-u2/2)。
In an embodiment of the present invention, have for auxiliary parameter, that is, smoothing parameter h to the estimation for returning receptance function
There is important influence.When h increases, the precision to recurrence receptance function estimation can be improved, but may cause and lose useful information
Residual error is caused to increase；When h reduces, although residual error can reduce, excessive fitting will cause, reduce and recurrence receptance function is estimated
The precision of meter.Wherein, it can use the method for returning cross validation for the selection of smoothing parameter h to choose, with appropriate
Estimate receptance function is returned.
Wherein, εtIt (s) is error term coefficient, wherein εt(s) desired value is 0.
In an embodiment of the present invention, the atmosphere of multiple air quality monitoring points can be calculated using regression analysis
The recurrence receptance function of pollutant concentration and meteorologic factor.
S120 constructs benchmark meteorological field using the historical data of meteorologic factor, and benchmark meteorological field is referring to for meteorologic factor
Surely the baseline probability distribution of region and specified monitoring time section is monitored.
In an embodiment of the present invention, in order to guarantee that air pollution concentration value can really reflect the discharge of pollutant
Amount, it is therefore desirable to remove meteorologic factor, that is to say, that under conditions of same meteorologic factor, different moments or different location
The discharge amount of atmosphere pollution is just comparable.
As an example, it is assumed that a certain air quality monitoring area o'clock of Beijing each year in 2012 to 2017
January atmosphere pollution discharge amount it is identical, but since the weather in January, 2014 is abnormal, lead to atmosphere pollution
The diffusion of object is accelerated, and the concentration value of the atmosphere pollution of as a result in January, 2014 monitoring is more dirty than the atmosphere in the January in other times
It is low to contaminate object concentration.It follows that the pollutant value of monitoring is only relied upon due to the influence of meteorologic factor, it can not
To in 2012 to 2017 each year January atmosphere pollution true discharge amount effectively compared.
In order to guarantee the accuracy to air evaluation quality, the historical data using meteorologic factor is needed, reference gas is established
Image field, so that pollutant value of the different air quality monitoring points in specified monitoring time section is in same reference gas
It is calculated under image field.
In an embodiment of the present invention, step S120 the following steps are included:
The historical data of meteorologic factor is normalized in S1201.
In an embodiment of the present invention, it in order to be compared the historical data of meteorologic factor in same level, needs
Data are normalized, make to be comparable between data.It as an example, can be by the history number of meteorologic factor
According to the decimal being converted between (0,1).
In order to further ensure the comparativity between the historical data of meteorologic factor, optionally, the history number of meteorologic factor
According to being the data acquired according to unified monitoring standard.
As an example, to the corresponding meteorological site of air quality monitoring point of above-mentioned Beijing at 2012-2017
The historical data of the meteorologic factor in each year January is normalized in year.
S1202 is analyzed multiple specified in specified monitoring region according to the historical data of the meteorologic factor of normalized
The Probability Characteristics of the meteorological site meteorologic factor under specified monitoring time section respectively.
In an embodiment of the present invention, specifying monitoring region includes multiple air quality monitoring points and multiple specified weather stations
Point.Probability Characteristics of the specified meteorological site under specified monitoring time section can be the probability density distribution letter of meteorologic factor
Number.Wherein, meteorologic factor includes at least any one of following item: temperature, air pressure, wind direction, dew-point temperature and wind speed.
In an embodiment of the present invention, Probability Characteristics of the specified meteorological site in specified monitoring time section are
It is obtained according to probability density function profiles of the specified meteorological site in specified monitoring time section under the conditions of multiple and different monitorings
's.
As an example, specifying meteorological site is Beijing A meteorological site, and specifying monitoring time section is Beijing A gas
As the spring of website.Specified monitoring time section under the conditions of multiple and different monitorings is that A meteorological site in Beijing was arrived in 2012
Each year spring in 2017.That is, different monitoring conditions is different the time.Then A meteorological site is within spring
Probability Characteristics be the flat of the probability density function of the meteorologic factor in each year spring in 2012 to 2017
Mean value.
As a specific example, the historical data of the meteorologic factor after normalized is utilized, it can be deduced that above-mentioned north
The probability density function f of capital city A meteorological site meteorologic factor in each year j season in -2017 years 2012aj(x, s '),
Wherein the value range of a be 1,2 ... ..6.As a=1, f1j(x, s ') represents the probability of the meteorologic factor in j season in 2012
Density fonction；As a=2, f2j(x, s ') represents the probability density function of the meteorologic factor in j season in 2013；
And so on, as a=6, f6j(x, s ') represents the probability density function of the meteorologic factor in j season in 2017.S ' is
Specified A meteorological site.
In this example, then the probability density function f. of A meteorological site meteorologic factor under j seasonj(x, s ') it can
To be calculated using following expression formula:
Wherein, 6 n, n are the number of specified monitoring condition, that is, the number in specified time.
In an embodiment of the present invention, it can use f.j(x, s ') calculates A meteorological site and goes in the j season of different year
Except the pollutant after meteorologic factor, so that pollutant of the A meteorological site in the j season of different year exists
It is comparable on time.Therefore, f.j(x, s ') it is referred to as time equilibrium density function.
In an embodiment of the present invention, using with method similar in above-mentioned example, specified monitoring region can be calculated
In multiple and different specified meteorological site respectively in the probability density function in j season, details are not described herein.That is,
According to the historical data of the meteorologic factor of acquisition, available multiple specified meteorological sites are respectively under specified monitoring time section
The probability density function of meteorologic factor.
S1203, according to the Probability Characteristics of meteorologic factor of multiple specified meteorological sites under specified monitoring time section,
Construct benchmark meteorological field.
In an embodiment of the present invention, in order to make the pollutant of air quality monitoring point not only in time may be used
Than also for realizing that the pollutant of each air quality monitoring point in specified monitoring region spatially can be into
Row compares, using the Probability Characteristics structure of multiple specified meteorological sites meteorologic factor under specified monitoring time section respectively
Build benchmark meteorological field so that the pollutant of the different air quality monitoring points in specified monitoring region in the time and
Spatially all have comparativity.
In an embodiment of the present invention, benchmark meteorological field is meteorologic factor in specified monitoring region and specified monitoring time section
Baseline probability distribution.That is, benchmark meteorological field is according to multiple specified meteorological site difference in specified monitoring region
What the Probability Characteristics of the meteorologic factor under specified monitoring time section obtained.
It as an example, include N number of meteorological site and M air quality monitoring point, N number of weather station in the R of target area
Point is located in set W.The baseline probability density fonction f. of benchmark meteorological fieldj(x) can use following expression formula indicates:
Wherein, s ' represents any meteorological site in W, f.j(x, s ') be meteorological site s ' under jth season it is meteorological because
The probability density function of element.That is, f.j(x) the benchmark meteorological field for being Target monitoring area R, as specified mesh
The baseline probability distribution of each air quality monitoring point corresponding meteorologic factor under specified monitoring time section in mark monitoring region R
Function.
In an embodiment of the present invention, benchmark meteorological field is spatially further on the basis of time equilibrium density function
Have adjusted meteorological condition.Therefore each air quality monitoring point in M air quality monitoring point is calculated under benchmark meteorological field
Pollutant, the pollutant of M air quality monitoring point can be made to all have over time and space can
Than property, and improve the accuracy of the concentration of atmosphere pollution.
S130, using the regression relation of pollutant and meteorologic factor, the atmosphere under calculating benchmark meteorological field is dirty
Object concentration is contaminated, to evaluate air quality.
In an embodiment of the present invention, step S130 the following steps are included:
According to the regression relation and benchmark meteorological field of pollutant and meteorologic factor, specified monitoring region is calculated
In air quality monitoring point in specified monitoring time section the mean concentration through benchmark meteorological field atmosphere pollution adjusted,
Mean intensity value includes at least any one of following item: daily mean of concentration value, monthly average concentration value, season mean intensity value and year
Mean intensity value；Or, calculate air quality monitoring point in specified monitoring region in specified monitoring time section through reference gas as
Field Distribution of air pollutant concentration adjusted is in specified percentile concentration value.
In an embodiment of the present invention, for specify air quality monitoring point in specified monitoring time section through reference gas
The mean concentration of image field atmosphere pollution adjusted, it is gentle using the pollutant in the air quality monitoring point
As the recurrence receptance function and benchmark meteorological field of factor are calculated.Wherein, through the atmosphere pollution adjusted of benchmark meteorological field
The concentration of object is to remove the concentration of the atmosphere pollution after meteorologic factor interference.
In an embodiment of the present invention, the baseline probability density point of utilization meteorologic factor adjusted over time and space
Cloth function can calculate the season mean concentration through benchmark meteorological field air quality monitoring point s adjusted 1 year jth season
μij(s).Wherein, μij(s) it can use following expression formula to be calculated:
Wherein,Refer to that each hour atmosphere is dirty in 1 year jth season according to air quality monitoring point s
Contaminate the concentration value of object and the historical data of corresponding meteorologic factor of each hour, the air quality monitoring point s obtained was at 1 year the
Recurrence receptance function m under j seasonijThe estimation of (x, s).f.jIt (x) is the baseline probability of the specified benchmark meteorological field for monitoring region
Density fonction.
As an example, the target area R of Beijing includes A air quality monitoring point, B air quality monitoring point and C
3 air quality monitoring points including air quality monitoring point.To calculate 1st season of the A air quality monitoring o'clock in 2013
It spends (spring) and temporally and spatially removes the season mean concentration μ of the atmosphere pollution after meteorologic factor1(A), then it needs
First with the concentration of A air quality monitoring o'clock each hour atmosphere pollution in n hour of spring in 2013 of monitoring
It is worth the historical data of meteorologic factor corresponding with each hour, obtains in A air quality monitoring o'clock under the conditions of spring in 2013
Recurrence receptance function m1The estimation of (x, A)
Then, the probability density function of the meteorologic factor in each year spring in 2013 to 2107 is carried out flat
, obtain A air quality monitoring point in the probability density function f. of spring corresponding benchmark meteorologic factor1(x, A).
Furthermore B air quality monitoring point is calculated separately out in the probability density distribution of spring corresponding benchmark meteorologic factor
Function f.1The probability density function f. of (x, B) and C air quality monitoring point in spring corresponding benchmark meteorologic factor1
(x, C).
Finally, calculating f.1(x, A), f.1(x, B) and f.1The average value f. of (x, C)1(x)。f.1It (x) is benchmark meteorological field
Baseline probability distribution.Then, f. is utilized1(x) corresponding spring in 2013 with A air quality monitoring o'clockIt calculates
A air quality monitoring point removes the season mean concentration μ in spring in 2013 of the atmosphere pollution after meteorologic factor1(A):
Wherein, B air quality monitoring o'clock can be calculated in spring atmosphere pollution in 2013 according to above-mentioned similar method
The season mean concentration μ of object1(B) and C air quality monitoring o'clock spring atmosphere pollution in 2013 season mean concentration μ1(C)。
The season mean concentration of atmosphere pollution due to different air quality monitorings o'clock spring in 2013 be over time and space into
Promoting the circulation of qi is as concentration adjusted, therefore μ1(A)、μ1(B) and μ1(C) it is spatially comparable.
In an embodiment of the present invention, similar, can be used similar method calculate the removal of air quality monitoring point it is meteorological because
The monthly average concentration and mean annual concentration isoconcentration value of atmosphere pollution after element.
In an embodiment of the present invention, for the Distribution of air pollutant concentration of the removal meteorologic factor on room and time
In specified percentile concentration value, it can use method similar with the mean concentration of above-mentioned calculating atmosphere pollution and counted
It calculates.
It is similar to expression formula (5), it is big 1 year jth season through benchmark meteorological field air quality monitoring point s adjusted
The q quantile concentration value ξ of gas pollutant concentrationij(q, s) can use following expression formula and be indicated:
Wherein, 0 < q < 1. It isInverse letter
Number.Wherein,It is FijThe estimation of (y'| x, s).Fij(y'| x, s)=P [yt(s)≤y'| x], indicate when it is meteorological because
When plain x is fixed, the pollutant of air quality monitoring point s is less than or equal to the conditional distribution function of y '.Wherein, y ' is gas
As the q quantile concentration value of the atmosphere pollution in 1 year jth season before adjustment.
Specifically,For air quality monitoring point s the atmosphere pollution in 1 year jth season q quartile
Particle density value and in each hour the corresponding meteorologic factor of q quantile concentration value historical data, the air quality monitoring obtained
Point s is in the pollutant in 1 year jth season and the recurrence receptance function F of meteorologic factorijThe estimation of (y'| x, s).f.j
It (x) is the baseline probability density fonction of the corresponding meteorologic factor of benchmark meteorological field.
Air Quality Evaluation method provided in an embodiment of the present invention, by over time and space to pollutant
Meteorological adjustment is carried out, influence of the meteorologic factor to pollutant had both been eliminated, and had improved the accurate of Air Quality Evaluation
Degree, and realize the concentration through meteorological atmosphere pollution adjusted of different air quality monitoring points over time and space
It can compare, in order to carry out regional air quality assessment.
In an embodiment of the present invention, regression analysis not only includes nonparametric kernel density estimation, further includes Parameter analysis and half
Parameter analysis therefore in some embodiments of the invention, can also be by constructing Partial Linear Models in step S1102
Or semi-parametric regression model is to substitute distribution-free regression procedure, and the Partial Linear Models or semi-parametric regression model of utilization building
Determine the regression relation of pollutant and meteorologic factor.
Wherein, Partial Linear Models are the functions with form known, but contain unknown parameter in the function.Pass through utilization
The principle of least square method, by the quadratic sum of measured value y gathered in advance and the difference of calculated value y 'Most
Small is optimized criterion, is utilizedLocal derviation is asked to different unknown parameters, and the partial derivative of each unknown parameter is enabled to be equal to 0, in turn
The available equation about unknown parameter.By the equation for solving unknown parameter, it can obtain in Partial Linear Models not
Know the estimated value of parameter.
In an embodiment of the present invention, the corresponding regression relation of Partial Linear Models can use following expression formula and carry out
It indicates:
yt(s)=β × yt-1(s)+m(xt(s), θ)+εt(s) (8)
Wherein, s is specified air quality monitoring point, yt(s) it is adopted for air quality monitoring point in specified monitoring time section
The pollutant of collection, yt-1(s) the upper monitoring time section for air quality monitoring point in specified monitoring time section is adopted
The pollutant of collection, β are the regression coefficient of Partial Linear Models, xtIt (s) is air quality monitoring point in specified monitoring
Period corresponding meteorologic factor, θ are the parameter of regression model, m (xt(s), θ) it is the recurrence receptance function constructed, εt(s) it is
Error term coefficient.
In an embodiment of the present invention, in conjunction with the principle of least square method, using the atmosphere pollution of monitoring concentration and
The historical data and regression parameter model of meteorologic factor can solve estimating for unknown parameter β and θ in Partial Linear Models
Evaluation, and then determine the concrete functional form of Partial Linear Models.Wherein, the functional form of receptance function is returned, it can be according to tool
Depending on body application scenarios, the embodiment of the present invention is not particularly limited.
Wherein, semi-parametric regression model had not only contained parametric component but also had contained nonparametric component, more can adequately utilize observation
Information provided by being worth, closer to truth.
In an embodiment of the present invention, the corresponding regression relation of semi-parameter model can use following expression formula carry out table
Show:
yt(s)=β × yt-1(s)+m(xt(s), s)+εt(s) (9)
Wherein, s is specified air quality monitoring point, yt(s) it is acquired for air quality monitoring point in specified monitoring time section
Pollutant, yt-1(s) the upper monitoring time section for air quality monitoring point in specified monitoring time section acquires
Pollutant, xtIt (s) is air quality monitoring in the corresponding meteorologic factor of specified monitoring time section, m (xt(s), s)
For the recurrence receptance function calculated according to the historical data of pollutant data and meteorologic factor, εtIt (s) is error term
Coefficient.
It in an embodiment of the present invention, can benefit for the unknown parameter β in the parametric component in semi-parametric regression model
It is determined with the historical data of the concentration of the atmosphere pollution of monitoring and meteorologic factor and in conjunction with least square method.Join for half
Nonparametric component m (x in number regression modelt(s), s), it can use local least squares method and estimated.
The Air Quality Evaluation method provided through the embodiment of the present invention is referred to by calculating under the same benchmark meteorological field
Surely multiple air quality monitoring points in region are monitored and eliminate meteorologic factor in the air pollution concentration of specified monitoring time section
It influences, ensure that air pollution concentration of the different air quality monitoring points in different time and different spaces is comparable,
Realize the accuracy to Air Quality Evaluation.
Fig. 2 shows the structural schematic diagram for the Air Quality Evaluation device 200 that an embodiment according to the present invention provides, the skies
Gas quality evaluation device includes:
Regression relation determining module 210, the history for pollutant data and meteorologic factor based on monitoring
Data determine the regression relation of pollutant and meteorologic factor using regression analysis；
Benchmark meteorological field constructs module 220, for constructing benchmark meteorological field, reference gas using the historical data of meteorologic factor
Image field is used to describe meteorologic factor in the distribution of the baseline probability of specified monitoring region and specified monitoring time section；
Pollutant computing module 230, for utilizing the regression relation of pollutant and meteorologic factor,
Pollutant under calculating benchmark meteorological field, to evaluate air quality.
In an embodiment of the present invention, regression relation determining module 210 is specifically used for:
Obtain air quality monitoring point the going through in the specified corresponding meteorologic factor of monitoring time section in specified monitoring region
History data；
Using regression analysis, the pollutant by air quality monitoring point in specified monitoring time section is expressed as
The regression function indicated by air quality monitoring point in the corresponding meteorologic factor of specified monitoring time section, is determined by regression function
The regression relation of pollutant and meteorologic factor.
In an embodiment of the present invention, regression relation determining module 210, is specifically used for:
Regression relation is constructed using non parametric regression algorithm, the expression formula of regression relation is yt(s)=m (xt(s), s)+εt
(s), wherein s is air quality monitoring point, ytIt (s) is air quality monitoring point in the atmosphere pollution for specifying monitoring time section
Concentration, xtIt (s) is air quality monitoring point in the corresponding meteorologic factor of specified monitoring time section, m (xt(s), s) it is according to atmosphere
The recurrence receptance function that the historical data of pollutant concentration data and meteorologic factor calculates, εtIt (s) is error term coefficient.
In an embodiment of the present invention, regression relation determining module 210, is specifically used for:
Partial Linear Models are constructed, determine that the recurrence of pollutant and meteorologic factor is closed by Partial Linear Models
System, wherein
The expression formula of the corresponding regression relation of Partial Linear Models are as follows: yt(s)=β × yt-1(s)+m(xt(s), θ)+εt
(s), wherein s is air quality monitoring point, ytIt (s) is air quality monitoring point in the atmosphere pollution for specifying monitoring time section
Concentration, yt-1(s) dense in the atmosphere pollution of a upper monitoring time section for specified monitoring time section for air quality monitoring point
Degree, β are the regression coefficient of regression model, xtIt (s) is air quality monitoring point in the corresponding meteorologic factor of specified monitoring time section,
θ is the parameter of regression model, m (xt(s), θ) it is the recurrence receptance function constructed, εtIt (s) is error term coefficient.
In an embodiment of the present invention, regression relation determining module 210, is specifically used for:
Semi-parameter model is constructed, the regression relation of pollutant and meteorologic factor is determined by semi-parameter model,
Wherein,
The expression formula of the corresponding regression relation of semi-parameter model are as follows: yt(s)=β × yt-1(s)+m(xt(s), s)+εt(s),
Wherein, s is air quality monitoring point in ytIt (s) is air quality monitoring point in the atmosphere pollution in specified monitoring time section
Concentration, yt-1(s) dense in the atmosphere pollution of the upper monitoring time section in specified monitoring time section for air quality monitoring point
Degree, xtIt (s) is air quality monitoring point in the corresponding meteorologic factor of specified monitoring time section, m (xt(s), s) it is according to atmosphere dirt
Contaminate the recurrence receptance function of the historical data calculating of object concentration data and meteorologic factor, εtIt (s) is error term coefficient.
In an embodiment of the present invention, benchmark meteorological field constructs module 220, is specifically used for:
The historical data of meteorologic factor is normalized；
According to the historical data of the meteorologic factor of normalized, multiple specified weather stations in specified monitoring region are analyzed
Put the Probability Characteristics of the meteorologic factor respectively under specified monitoring time section；
According to the Probability Characteristics of multiple specified meteorological sites meteorologic factor under specified monitoring time section respectively, structure
Build benchmark meteorological field.
In an embodiment of the present invention, meteorologic factor includes at least any one of following item: temperature, air pressure, wind direction, dew
Point temperature and wind speed.
In an embodiment of the present invention, air pollution concentration computing module 230, is specifically used for:
It is distributed according to pollutant and the regression relation and baseline probability of meteorologic factor, calculates specified monitoring section
Air quality monitoring point in domain is average dense through benchmark meteorological field atmosphere pollution adjusted in specified monitoring time section
Degree, mean intensity value include at least any one of following item: daily mean of concentration value, monthly average concentration value, season mean intensity value
With mean annual concentration value；Or,
It calculates and specifies the air quality monitoring point in monitoring region in specified monitoring time section after the adjustment of benchmark meteorological field
Distribution of air pollutant concentration in specified percentile concentration value.
Air Quality Evaluation device provided in an embodiment of the present invention, by using monitoring pollutant data and
The regression relation of pollutant and meteorologic factor that the historical data of meteorologic factor determines, and building reference gas as
, the pollutant under benchmark meteorological field is obtained, ensure that the air pollution concentration of calculating really reflects atmosphere dirt
The discharge amount for contaminating concentration, realizes the accuracy of Air Quality Evaluation.
The other details of Air Quality Evaluation device according to an embodiment of the present invention combine Fig. 1 to Fig. 2 to describe with more than
Air Quality Evaluation method according to an embodiment of the present invention is similar, and details are not described herein.
It can be by air in conjunction with Fig. 1 to Fig. 2 Air Quality Evaluation method and apparatus according to an embodiment of the present invention described
Quality evaluation equipment is realized.Fig. 3 is to show to be illustrated according to the hardware configuration 300 of the Air Quality Evaluation equipment of inventive embodiments
Figure.
As shown in figure 3, the Air Quality Evaluation equipment 300 in the present embodiment includes: processor 301, memory 302, leads to
Believe interface 303 and bus 310, wherein processor 301, memory 302, communication interface 303 are connected and completed by bus 310
Mutual communication.
Specifically, above-mentioned processor 301 may include central processing unit (CPU) or specific integrated circuit (ASIC), or
Person may be configured to implement one or more integrated circuits of the embodiment of the present invention.
Memory 302 may include the mass storage for data or instruction.For example it rather than limits, memory
302 may include HDD, floppy disk drive, flash memory, CD, magneto-optic disk, tape or universal serial bus (USB) driver or two
The combination of a or more the above.In a suitable case, memory 302 may include that can be removed or non-removable (or solid
Medium calmly).In a suitable case, memory 302 can be inside or outside Air Quality Evaluation equipment 300.Specific
In embodiment, memory 302 is non-volatile solid state memory.In a particular embodiment, memory 302 includes read-only memory
(ROM).In a suitable case, which can be the ROM of masked edit program, programming ROM (PROM), erasable PROM
(EPROM), electric erasable PROM (EEPROM), electrically-alterable ROM (EAROM) or flash memory or two or more the above
Combination.
Communication interface 303 is mainly used for realizing in the embodiment of the present invention between each module, device, unit and/or equipment
Communication.
Bus 310 includes hardware, software or both, and the component of Air Quality Evaluation equipment 300 is coupled to each other together.
For example it rather than limits, bus may include accelerated graphics port (AGP) or other graphics bus, enhancing Industry Standard Architecture
(EISA) bus, front side bus (FSB), super transmission (HT) interconnection, Industry Standard Architecture (ISA) bus, infinite bandwidth interconnect, are low
Number of pins (LPC) bus, memory bus, micro- channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-
Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association part (VLB) bus or
The combination of other suitable buses or two or more the above.In a suitable case, bus 310 may include one
Or multiple buses.Although specific bus has been described and illustrated in the embodiment of the present invention, the present invention considers any suitable bus
Or interconnection.
That is, Air Quality Evaluation equipment 300 shown in Fig. 3 may be implemented as including: processor 301, storage
Device 302, communication interface 303 and bus 310.Processor 301, memory 302 and communication interface 303 are connected simultaneously by bus 310
Complete mutual communication.Memory 302 is for storing program code；Processor 301 is stored by reading in memory 302
Executable program code runs program corresponding with executable program code, for executing in any embodiment of the present invention
Air Quality Evaluation method, to realize the Air Quality Evaluation method and apparatus described in conjunction with Fig. 1 to Fig. 2.
The embodiment of the present invention also provides a kind of computer storage medium, and computer journey is stored in the computer storage medium
Sequence instruction；The computer program instructions realize Air Quality Evaluation method provided in an embodiment of the present invention when being executed by processor.
It should be clear that the invention is not limited to specific configuration described above and shown in figure and processing.
For brevity, it is omitted here the detailed description to known method.In the above-described embodiments, several tools have been described and illustrated
The step of body, is as example.But method process of the invention is not limited to described and illustrated specific steps, this field
Technical staff can be variously modified, modification and addition after understanding spirit of the invention, or suitable between changing the step
Sequence.
Functional block shown in above structural block diagram can be implemented as hardware, software, firmware or their combination.When
When realizing in hardware, electronic circuit, specific integrated circuit (ASIC), firmware appropriate, plug-in unit, function may, for example, be
Card etc..When being realized with software mode, element of the invention is used to execute the program or code segment of required task.Journey
Sequence perhaps code segment can store in machine readable media or the data-signal by being carried in carrier wave in transmission medium or
Person's communication links are sent." machine readable media " may include any medium for capableing of storage or transmission information.It is machine readable
The example of medium include electronic circuit, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disk, CD-ROM,
CD, hard disk, fiber medium, radio frequency (RF) link, etc..Code segment can be via the calculating of internet, Intranet etc.
Machine network is downloaded.
It should also be noted that, the exemplary embodiment referred in the present invention, is retouched based on a series of step or device
State certain methods or system.But the present invention is not limited to the sequence of above-mentioned steps, that is to say, that can be according in embodiment
The sequence referred to executes step, may also be distinct from that the sequence in embodiment or several steps are performed simultaneously.
More than, only a specific embodiment of the invention, it is apparent to those skilled in the art that, in order to
Convenienct and succinct, system, the specific work process of module and unit of foregoing description of description can be implemented with reference to preceding method
Corresponding process in example, details are not described herein.It should be understood that scope of protection of the present invention is not limited thereto, it is any to be familiar with this skill
The technical staff in art field in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or substitutions, these
Modifications or substitutions should be covered by the protection scope of the present invention.
Claims (11)
1. a kind of Air Quality Evaluation method, which is characterized in that the Air Quality Evaluation method includes:
The historical data of pollutant data and meteorologic factor based on monitoring determines atmosphere using regression analysis
The regression relation of pollutant concentration and the meteorologic factor；
Construct benchmark meteorological field using the historical data of the meteorologic factor, the benchmark meteorological field for describe it is described it is meteorological because
Element is in the distribution of the baseline probability of specified monitoring region and specified monitoring time section；
Using the regression relation of the pollutant and the meteorologic factor, the atmosphere under the benchmark meteorological field is calculated
Pollutant concentration, to evaluate air quality.
2. Air Quality Evaluation method according to claim 1, which is characterized in that the atmosphere pollution based on monitoring
The historical data of concentration data and meteorologic factor determines pollutant and the meteorologic factor using regression analysis
Regression relation, comprising:
The air quality monitoring point in specified monitoring region is obtained in the history number of the specified corresponding meteorologic factor of monitoring time section
According to；
It is using the regression analysis, the air quality monitoring point is dense in the atmosphere pollution of the specified monitoring time section
Degree is expressed as the recurrence indicated by the air quality monitoring point in the corresponding meteorologic factor of the specified monitoring time section
Function determines the regression relation of the pollutant and the meteorologic factor by the regression function.
3. Air Quality Evaluation method according to claim 2, which is characterized in that the method using regression analysis,
Pollutant by the air quality monitoring point in the specified monitoring time section is expressed as by the air quality
The regression function that monitoring point is indicated in the corresponding meteorologic factor of the specified monitoring time section, comprising:
The regression relation is constructed using non parametric regression algorithm, the expression formula of the regression relation is yt(s)=m (xt(s), s)
+εt(s), wherein s is air quality monitoring point, ytIt (s) is the air quality monitoring point in specified monitoring time section acquisition
Pollutant, xtIt (s) is the air quality monitoring point in the corresponding meteorologic factor of specified monitoring time section, m (xt
(s), s) it is the recurrence receptance function calculated according to the historical data of the pollutant data and the meteorologic factor,
The εtIt (s) is error term coefficient.
4. Air Quality Evaluation method according to claim 2, which is characterized in that it is described to utilize the regression analysis,
Pollutant by the air quality monitoring point in the specified monitoring time section is expressed as by the air quality
The regression function that monitoring point is indicated in the corresponding meteorologic factor of the specified monitoring time section, comprising:
Partial Linear Models are constructed, determine the pollutant and the meteorologic factor by the Partial Linear Models
Regression relation, wherein
The expression formula of the corresponding regression relation of the Partial Linear Models are as follows: yt(s)=β × yt-1(s)+m(xt(s), θ)+εt
(s), wherein s is air quality monitoring point, ytIt (s) is the air quality monitoring point in the big of specified monitoring time section acquisition
Gas pollutant concentration, yt-1It (s) is a upper monitoring time section of the air quality monitoring point in the specified monitoring time section
The pollutant of acquisition, β are the regression coefficient of the regression model, xtIt (s) is the air quality monitoring point in institute
The corresponding meteorologic factor of specified monitoring time section is stated, θ is the parameter of the regression model, m (xt(s), θ) it is that the recurrence constructed is rung
Answer function, the εtIt (s) is error term coefficient.
5. Air Quality Evaluation method according to claim 2, which is characterized in that it is described to utilize the regression analysis,
Pollutant by the air quality monitoring point in the specified monitoring time section is expressed as by the air quality
The regression function that monitoring point is indicated in the corresponding meteorologic factor of specified monitoring time section, comprising:
Semi-parameter model is constructed, time of the pollutant and the meteorologic factor is determined by the semi-parameter model
Return relationship, wherein
The expression formula of the corresponding regression relation of the semi-parameter model are as follows: yt(s)=β × yt-1(s)+m(xt(s), s)+εt(s),
Wherein, s is air quality monitoring point, yt(s) dirty in the atmosphere of specified monitoring time section acquisition for the air quality monitoring point
Contaminate object concentration, yt-1(s) the upper monitoring time section for the air quality monitoring point in the specified monitoring time section acquires
Pollutant, xtIt (s) is the air quality monitoring point in the corresponding meteorologic factor of specified monitoring time section, m (xt
(s), s) it is the recurrence receptance function calculated according to the historical data of the pollutant data and the meteorologic factor,
The εtIt (s) is error term coefficient.
6. Air Quality Evaluation method according to claim 1, which is characterized in that the going through using the meteorologic factor
History data construct benchmark meteorological field, comprising:
The historical data of the meteorologic factor is normalized；
According to the historical data of the meteorologic factor of the normalized, multiple specified gas in the specified monitoring region are analyzed
As the Probability Characteristics of the website meteorologic factor under the specified monitoring time section respectively；
Probability distribution according to the multiple specified meteorological site meteorologic factor under specified monitoring time section respectively is special
Sign, constructs the benchmark meteorological field.
7. Air Quality Evaluation method according to claim 1, which is characterized in that the meteorologic factor includes at least as follows
Any one of: temperature, air pressure, wind direction, dew-point temperature and wind speed.
8. Air Quality Evaluation method according to claim 1, which is characterized in that described dense using the atmosphere pollution
The regression relation of degree and the meteorologic factor, calculates the pollutant value under the benchmark meteorological field, comprising:
According to the regression relation and baseline probability distribution of pollutant and the meteorologic factor, the finger is calculated
Surely it is adjusted big through the benchmark meteorological field in the specified monitoring time section to monitor the air quality monitoring point in region
The mean concentration of gas pollutant, the mean intensity value include at least any one of following item: daily mean of concentration value, monthly average
Concentration value, season mean intensity value and mean annual concentration value；
Or,
The air quality monitoring point in the specified monitoring region is calculated in the specified monitoring time section through the reference gas
Image field Distribution of air pollutant concentration adjusted is in specified percentile concentration value.
9. a kind of Air Quality Evaluation device, which is characterized in that described device includes:
Regression relation determining module, for the historical data of pollutant data and meteorologic factor based on monitoring, benefit
With regression analysis, the regression relation of pollutant and the meteorologic factor is determined；
Benchmark meteorological field constructs module, for constructing benchmark meteorological field, the benchmark using the historical data of the meteorologic factor
Meteorological field is used to describe the meteorologic factor in the distribution of the baseline probability of specified monitoring region and specified monitoring time section；
Air pollution concentration computing module, for utilizing the regression relation of the pollutant and the meteorologic factor,
The pollutant under the benchmark meteorological field is calculated, to evaluate air quality.
10. a kind of Air Quality Evaluation equipment, which is characterized in that the equipment includes: processor and is stored with computer journey
The memory of sequence instruction；
The processor realizes the air quality as described in claim 1-8 any one when executing the computer program instructions
Evaluation method.
11. a kind of computer storage medium, which is characterized in that be stored with computer program in the computer storage medium and refer to
It enables, realizes that the air quality as described in claim 1-8 any one is commented when the computer program instructions are executed by processor
Valence method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811183512.0A CN109298136B (en) | 2018-10-11 | 2018-10-11 | Air Quality Evaluation method, apparatus, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811183512.0A CN109298136B (en) | 2018-10-11 | 2018-10-11 | Air Quality Evaluation method, apparatus, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109298136A true CN109298136A (en) | 2019-02-01 |
| CN109298136B CN109298136B (en) | 2019-10-15 |
Family
ID=65162410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811183512.0A Active CN109298136B (en) | 2018-10-11 | 2018-10-11 | Air Quality Evaluation method, apparatus, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109298136B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110333556A (en) * | 2019-06-03 | 2019-10-15 | 深圳中兴网信科技有限公司 | Air Quality Forecast method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN110531029A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of device based on environmentally friendly Internet of Things big data prediction air quality trend |
| CN111189152A (en) * | 2020-01-11 | 2020-05-22 | 武汉科正工程技术有限公司 | Method and system for detecting indoor environment quality |
| CN111581808A (en) * | 2020-04-30 | 2020-08-25 | 中科三清科技有限公司 | Pollutant information processing method and device, storage medium and terminal |
| CN111882205A (en) * | 2020-07-24 | 2020-11-03 | 中科三清科技有限公司 | Air quality standard-reaching analysis method and device, electronic equipment and storage medium |
| CN112036243A (en) * | 2020-07-28 | 2020-12-04 | 广州地理研究所 | Method, device and equipment for measuring atmospheric pollution of traffic road |
| CN112509288A (en) * | 2020-09-28 | 2021-03-16 | 北京英视睿达科技有限公司 | Monitoring method and device for atmospheric pollution, electronic equipment and medium |
| CN113330283A (en) * | 2018-08-25 | 2021-08-31 | 山东诺方电子科技有限公司 | Data reliability evaluation and calibration method for atmospheric pollution detection equipment |
| WO2021179742A1 (en) * | 2020-03-10 | 2021-09-16 | 中国科学院深圳先进技术研究院 | Ozone missing data interpolation method, apparatus and device |
| CN115436570A (en) * | 2022-08-25 | 2022-12-06 | 二十一世纪空间技术应用股份有限公司 | Carbon dioxide concentration remote sensing monitoring method and device based on multivariate data |
| CN116776073A (en) * | 2023-08-14 | 2023-09-19 | 中科三清科技有限公司 | Pollutant concentration evaluation method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069537A (en) * | 2015-08-25 | 2015-11-18 | 中山大学 | Constructing method of combined air quality forecasting model |
| CN106295905A (en) * | 2016-08-22 | 2017-01-04 | 南京大学 | A kind of air quality based on Lagrange conveying model is quickly traced to the source forecasting procedure |
| CN108053071A (en) * | 2017-12-21 | 2018-05-18 | 宇星科技发展(深圳)有限公司 | Regional air pollutant concentration Forecasting Methodology, terminal and readable storage medium storing program for executing |
| CN108426812A (en) * | 2018-04-08 | 2018-08-21 | 浙江工业大学 | A kind of PM2.5 concentration value prediction techniques based on Memory Neural Networks |
| CN108537383A (en) * | 2018-04-09 | 2018-09-14 | 山东建筑大学 | A kind of room air prediction technique based on Model Fusion |
-
2018
- 2018-10-11 CN CN201811183512.0A patent/CN109298136B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069537A (en) * | 2015-08-25 | 2015-11-18 | 中山大学 | Constructing method of combined air quality forecasting model |
| CN106295905A (en) * | 2016-08-22 | 2017-01-04 | 南京大学 | A kind of air quality based on Lagrange conveying model is quickly traced to the source forecasting procedure |
| CN108053071A (en) * | 2017-12-21 | 2018-05-18 | 宇星科技发展(深圳)有限公司 | Regional air pollutant concentration Forecasting Methodology, terminal and readable storage medium storing program for executing |
| CN108426812A (en) * | 2018-04-08 | 2018-08-21 | 浙江工业大学 | A kind of PM2.5 concentration value prediction techniques based on Memory Neural Networks |
| CN108537383A (en) * | 2018-04-09 | 2018-09-14 | 山东建筑大学 | A kind of room air prediction technique based on Model Fusion |
Non-Patent Citations (2)
| Title |
|---|
| 翟宇梅 等: "K近邻非参数回归概率预报技术及其应用", 《应用气象学报》 * |
| 胡玉萍 等: "截断情形下污染数据半参数回归模型估计方法", 《郑州大学学报(工学版)》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113330283B (en) * | 2018-08-25 | 2023-03-21 | 山东诺方电子科技有限公司 | Data reliability evaluation and calibration method for atmospheric pollution detection equipment |
| CN113330283A (en) * | 2018-08-25 | 2021-08-31 | 山东诺方电子科技有限公司 | Data reliability evaluation and calibration method for atmospheric pollution detection equipment |
| CN110333556A (en) * | 2019-06-03 | 2019-10-15 | 深圳中兴网信科技有限公司 | Air Quality Forecast method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN110531029A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of device based on environmentally friendly Internet of Things big data prediction air quality trend |
| CN110531029B (en) * | 2019-08-16 | 2022-02-25 | 北京慧辰资道资讯股份有限公司 | Device for predicting air quality trend based on environmental protection Internet of things big data |
| CN111189152A (en) * | 2020-01-11 | 2020-05-22 | 武汉科正工程技术有限公司 | Method and system for detecting indoor environment quality |
| CN111189152B (en) * | 2020-01-11 | 2021-05-18 | 武汉科正工程技术有限公司 | Method and system for detecting indoor environment quality |
| WO2021179742A1 (en) * | 2020-03-10 | 2021-09-16 | 中国科学院深圳先进技术研究院 | Ozone missing data interpolation method, apparatus and device |
| CN111581808A (en) * | 2020-04-30 | 2020-08-25 | 中科三清科技有限公司 | Pollutant information processing method and device, storage medium and terminal |
| CN111882205A (en) * | 2020-07-24 | 2020-11-03 | 中科三清科技有限公司 | Air quality standard-reaching analysis method and device, electronic equipment and storage medium |
| CN112036243A (en) * | 2020-07-28 | 2020-12-04 | 广州地理研究所 | Method, device and equipment for measuring atmospheric pollution of traffic road |
| CN112509288B (en) * | 2020-09-28 | 2022-01-14 | 北京英视睿达科技有限公司 | Monitoring method and device for atmospheric pollution, electronic equipment and medium |
| CN112509288A (en) * | 2020-09-28 | 2021-03-16 | 北京英视睿达科技有限公司 | Monitoring method and device for atmospheric pollution, electronic equipment and medium |
| CN115436570A (en) * | 2022-08-25 | 2022-12-06 | 二十一世纪空间技术应用股份有限公司 | Carbon dioxide concentration remote sensing monitoring method and device based on multivariate data |
| CN116776073A (en) * | 2023-08-14 | 2023-09-19 | 中科三清科技有限公司 | Pollutant concentration evaluation method and device |
| CN116776073B (en) * | 2023-08-14 | 2023-11-21 | 中科三清科技有限公司 | Pollutant concentration evaluation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109298136B (en) | 2019-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109298136B (en) | Air Quality Evaluation method, apparatus, equipment and storage medium | |
| CN105740991B (en) | Climate change prediction method and system based on improved BP neural network fitting of multiple climate modes | |
| Mahmud et al. | Monthly rainfall forecast of Bangladesh using autoregressive integrated moving average method | |
| Suhaila et al. | Comparing rainfall patterns between regions in Peninsular Malaysia via a functional data analysis technique | |
| Steinschneider et al. | Toward a statistical framework to quantify the uncertainties of hydrologic response under climate change | |
| Drobinski et al. | Surface wind-speed statistics modelling: Alternatives to the Weibull distribution and performance evaluation | |
| CN106878375A (en) | A kind of cockpit pollutant monitoring method based on distribution combination sensor network | |
| CN104809333A (en) | Capacity predicating method and system based on Kalman filter | |
| CN111242404B (en) | Extreme evaluation method and system for heavy rainfall induced flood incident | |
| CN110687255A (en) | Air pollutant tracing method, device, equipment and storage medium | |
| Dzupire et al. | A poisson-gamma model for zero inflated rainfall data | |
| Strecker et al. | Parameter identification of a ground‐water contaminant transport model | |
| CN110738354B (en) | Method and device for predicting particulate matter concentration, storage medium and electronic equipment | |
| CN108009972A (en) | A kind of multimode trip O-D needs estimate methods checked based on multi-source data | |
| El-Mallah et al. | Time-series modeling and short term prediction of annual temperature trend on Coast Libya using the box-Jenkins ARIMA Model | |
| Fiener et al. | Comment on" The new assessment of soil loss by water erosion in Europe" by Panagos et al.(Environmental Science & Policy 54 (2015) 438–447) | |
| Jamil et al. | On the calibration and applicability of global solar radiation models based on temperature extremities in India | |
| Sharma et al. | Forecasts using Box–Jenkins models for the ambient air quality data of Delhi City | |
| Valdez-Cepeda et al. | Fractality of monthly extreme minimum temperature | |
| Tahrudi et al. | Evaluation the trend and trend change point of Urmia Lake basin precipitation. | |
| Halimi et al. | Modeling spatial distribution of Tehran air pollutants using geostatistical methods incorporate uncertainty maps | |
| CN112712220B (en) | Method and device for estimating ground ozone concentration and computer equipment | |
| CN103033274A (en) | Measuring method of solar temperature probability density | |
| CN111461163B (en) | Urban interior PM2.5 concentration simulation and population exposure evaluation method and device | |
| Rao et al. | Resampling and extreme value statistics in air quality model performance evaluation |
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 |