CN102799772A - Air quality forecast oriented sample optimization method - Google Patents
Air quality forecast oriented sample optimization method Download PDFInfo
- Publication number
- CN102799772A CN102799772A CN2012102288175A CN201210228817A CN102799772A CN 102799772 A CN102799772 A CN 102799772A CN 2012102288175 A CN2012102288175 A CN 2012102288175A CN 201210228817 A CN201210228817 A CN 201210228817A CN 102799772 A CN102799772 A CN 102799772A
- Authority
- CN
- China
- Prior art keywords
- meteorological
- factor
- sample
- value
- meteorological factor
- 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 43
- 238000005457 optimization Methods 0.000 title claims abstract description 31
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 45
- 231100000719 pollutant Toxicity 0.000 claims abstract description 45
- 239000011159 matrix material Substances 0.000 claims abstract description 28
- 238000012216 screening Methods 0.000 claims abstract description 28
- 238000002474 experimental method Methods 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 9
- 230000005855 radiation Effects 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 6
- 241000894007 species Species 0.000 claims description 6
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000000556 factor analysis Methods 0.000 claims description 3
- 238000001308 synthesis method Methods 0.000 claims description 3
- 241001269238 Data Species 0.000 claims description 2
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 claims description 2
- 238000005303 weighing Methods 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 5
- 230000006872 improvement Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000009792 diffusion process Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- ZXVONLUNISGICL-UHFFFAOYSA-N 4,6-dinitro-o-cresol Chemical compound CC1=CC([N+]([O-])=O)=CC([N+]([O-])=O)=C1O ZXVONLUNISGICL-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 210000002364 input neuron Anatomy 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Abstract
The invention aims to solve the technical problem of providing an air quality forecast oriented sample optimization method which is high in forecast accuracy and good in adaptability. The method comprises the following steps: (1) determining relevant parameters of sample optimized screening, which is concretely implemented as follows: (1.1) determining a meteorological factor weight matrix by using a method for carrying out comprehensive analysis on pollutant concentrations and meteorological factors; (1.2) determining a threshold matrix by using an orthogonal experimental method; and (1.3) determining a sample size by using an experiment checking method; and (2) carrying out optimized screening on samples by using the determined parameters, which is concretely implemented as follows: (2.1) screening out samples with a meteorological similarity reaching a threshold range; (2.2) screening out samples with an overall meteorological similarity reaching the threshold range; and (2.3) screening out samples with a meteorological background which has the highest similarity with the meteorological background at the forecast date.
Description
Technical field
The invention belongs to the environmental forecasting field, particularly air quality prediction field.
Background technology
From the nineties in 20th century, artificial neural network begins to be applied to air quality prediction field.Artificial neural network plays the effect of data-driven in the prediction of air quality process.Calculate and draw the output layer neuron by input layer through neural network structure.Neural network structure is adjusted through the learning process of historical data and is finally confirmed.
Improve constantly along with what forecast precision required, the use and the improvement of neural network are studied also in progressively development.The BP neural network is a kind of artificial neural network that utilizes error backpropagation algorithm; Through continuous repetition propagated forward and back-propagating process; Satisfy termination condition until each training mode; Then study finishes, thereby utilizes the network structure of accomplishing after learning, and draws according to prediction day input neuron information to predict the outcome.
See that from the aspect of modelling the factor of the e-learning that affects the nerves and generalization ability mainly contains three: network topology structure, learning algorithm and learning sample.Aspect the improvement of forecasting procedure, mainly concentrating on network structure and the learning algorithm, many scholars have done many researchs, have improved the precision of prediction of network to a certain extent, have obtained certain achievement.But the raising to prediction of air quality model prediction degree of accuracy after the improvement of network structure and learning algorithm acquires a certain degree just limits to some extent.So outside to network structure and learning algorithm improvement, the selection of learning sample just becomes the final factor of decision network mapping and generalization ability.Because the selection of learning sample makes learning sample representative, can remove unnecessary interference, reaches the purpose of the excellent product of excellent kind.Say from physical angle; Influencing the atmosphere pollution diffusion is meteorological condition with the principal element of carrying; Foundation becomes primary selection based on the sample optimization method of meteorological similarity criterion; Because different meteorological factors have different influences to pollutant levels, the interaction between meteorological factor, the comprehensive weather environment that forms also have Different Effects to pollutant, cause inconstant corresponding relation between meteorological Changing Pattern and pollutant levels.Polynary meteorologic factor is moulded various meteorological space, and there is different influences in different meteorological spaces to the transmission and the diffusion of pollutant.The similarity in meteorological space has regular reference to the variation of pollutant levels.When carrying out prediction of air quality, if the meteorological space of seeking suitablely, the internal relation between a plurality of physical quantitys and pollutant has just had reference.Select suitable sample set to major influence factors, make forecast work have more specific aim, improved network mapping and generalization ability, may ultimately reach the purpose that improves the prediction of air quality degree of accuracy.
Summary of the invention
The technical matters that the present invention solves provide a kind of forecast precision high, the good sample optimization method towards prediction of air quality with strong points of adaptivity.
For solving the problems of the technologies described above, the technical scheme that the present invention adopts is: a kind of sample optimization method towards prediction of air quality is provided, it is characterized in that, may further comprise the steps:
(1) confirm the correlation parameter of sample optimization screening, its specifically:
(11) adopt pollutant levels and meteorological factor analysis by synthesis method to confirm the meteorological factor weight matrix, its specifically:
(111) obtain meteorological factor weighted value under the pollutant rise and fall sight;
(112) obtain meteorological factor weighted value under the serious and slight sight of pollutant;
(113) related coefficient of calculating pollutant quality concentration and meteorological factor;
(114) calculate the initial weight value of each meteorological factor, set up weight matrix;
(12) adopt orthogonal experiment method to confirm threshold matrix;
(13) confirm sample size;
(2) filter out the sample of optimization, its specifically:
(21) filter out each meteorological similarity and reach the sample in the threshold range;
(22) filter out overall meteorological similarity and reach the sample in the threshold range;
(23) filter out and predict day the highest sample of meteorological background similarity.
The concrete steps of said step (111) are:
(1111) obtain sight meteorological factor representative data once; The up-down value that is pollutant concentration today and concentration contrast yesterday respectively more than 0.05mg/m3 and-average and maximal value, minimum value and the mean value of analyzing this meteorological factor in the period of interim each meteorological factor during below the 0.05mg/m3 two; Be upward period mean value
, downward period mean value
and maximal value
, minimum value
and the mean value
of analyzing the period, wherein
is the meteorological factor label;
(1112) numerical value normalization is handled, and the utilization following formula is handled,
(1113) calculate meteorological factor change degree,
;
(1114) calculate weighted value;
; Wherein
is the meteorological factor change degree, and
is the meteorological factor species number.
The concrete steps of said step (112) are:
(1121) obtain two times meteorological factor representative datas of sight; The API value that is pollutant is maximal value, minimum value and the mean value of this meteorological factor in the average of each meteorological factor more than 100 and in two periods below 20 and analysis period respectively; Be seriously polluted mean value in period
, pollute slight mean value in period
and maximal value
, minimum value
and the mean value
of analysis period, wherein
is the meteorological factor label;
(1122) numerical value normalization is handled, and the utilization following formula is handled,
，
，
；
(1123) calculate meteorological factor change degree,
;
(1124) calculate weighted value;
; Wherein
is the meteorological factor change degree, and
is the meteorological factor species number.
The related coefficient of pollutant quality concentration and meteorological factor is described in the said step (113):
The initial weight value of each meteorological factor is described in the said step (114):
Where,
is the correlation coefficient;
and
, respectively under scenario one and scenario two weight values calculated.
The concrete steps of step (12) are:
(121) confirm that experimental index is model prediction result's a absolute error value;
(122) select factor, decide level, need to confirm the experimental factor investigated according to the result of S1 step weight matrix, in this patent, promptly choose the big meteorologic factor of pollutant levels weighing factor value as experimental factor, and draft the level of each factor;
(123) design the orthogonal table gauge outfit, experimental factor is filled into the row of orthogonal table respectively;
(124) insert each level numeral the row of orthogonal table;
(125) value of calculating
, wherein
be
row factor
pairing test index of level with;
(126) calculate the mean value
of the same level of each factor,
is the mean value of
(127) calculate the extreme difference
of each factor
(128) optimal combination is confirmed excellent level according to the mean value
of each factor level.
The method of definite employing experimental check of said step (13) sample size adopts a plurality of sample sizes to make an experiment respectively to every kind of pollutant, chooses a best sample size of model prediction effect, and promptly precision of prediction is the highest.
The screening mechanism of said step (2) Screening Samples is similar with meteorology to be criterion.
The concrete steps of said step (2) are:
(21) filter out each meteorological similarity and all reach the sample in the assign thresholds scope, concrete grammar is:
Sample must satisfy following formula:
In the formula,
is the prediction meteorological factor value of day;
is the meteorological similarity between sample and prediction day each meteorological factor;
(22) filter out overall meteorological similarity and reach the sample in certain threshold range, the sample that filters out must satisfy following formula:
In the formula,
is overall meteorological similarity;
(23) filter out and predict day the highest
bar sample of meteorological background similarity.The sample that filters out must satisfy following formula:
In the formula,
is the ascending order sample row with overall meteorological similarity
ordering;
Compare with existing prediction of air quality method based on neural network, three layers of sample of meteorological similarity criterion are optimized screening technique has the following advantages the prediction of air quality of artificial neural network:
1, the sample optimization method to every kind of pollutant all pointed and practicality.Identical meteorological spatial field is different to the change in concentration influence of different pollutants.Every kind of pollutant is the characteristic meteorological factor of influential its change in concentration all, and they are to the pollutant effects degree varies.Through the characteristic meteorological factor of every kind of pollutant of definite influence and to the pollutant effects degree, the sample of optimization will have more specific aim.
2, the sample optimization method changes pointed to prediction day pollutant levels.The meteorological spatial field of different times exists than big-difference, although period is close, owing to receive the influence of cold air, typhoon or other special meteorologies, the meteorological spatial field on close date also may not be identical.To predict day same day and background meteorology thereof as optimizing criterion, through in historical data base, searching relative meteorological condition, choose the most close meteorological spatial field, set up forecasting model with this.As far as prediction day pollutant situation of change, will have more specific aim.
Description of drawings
Fig. 1 is that three layers of sample are optimized screening process;
Fig. 2 is a ground floor screening sample flow process;
Fig. 3 is a second layer screening sample flow process;
Fig. 4 is the 3rd a layer of screening sample flow process;
Fig. 5 is the orthogonal experiments analysis process;
Fig. 6 is that weight matrix is confirmed method flow.
Embodiment
Come the present invention is further specified in conjunction with accompanying drawing and embodiment.
The present invention provides a kind of sample optimization method towards prediction of air quality, it is characterized in that, may further comprise the steps:
(1) confirm the correlation parameter of sample optimization screening, its specifically:
(11) adopt pollutant levels and meteorological factor analysis by synthesis method to confirm the meteorological factor weight matrix, its specifically:
(111) obtain meteorological factor weighted value under the pollutant rise and fall sight;
(112) obtain meteorological factor weighted value under the serious and slight sight of pollutant;
(113) related coefficient of calculating pollutant quality concentration and meteorological factor;
(114) calculate the initial weight value of each meteorological factor, set up weight matrix;
(12) adopt orthogonal experiment method to confirm threshold matrix;
(13) confirm sample size;
(2) Screening Samples obtains the sample of optimizing.
Present invention is described below in conjunction with real example: prepare data: environment automatic monitoring station, somewhere PM10 mass concentration, meteorologic factor (temperature, air pressure, wind speed, wind direction, solar radiation, rainfall amount, relative humidity).
(1) sample optimization screening correlation parameter is confirmed
(11): the confirming of weight matrix
(111): pollutant rise and fall sight meteorological factor weighted value
(1111): the meteorological factor typical value is calculated as follows:
Table 1 meteorological factor typical value
(1112): numerical value normalization is calculated
(1113): the meteorological factor change degree calculates
(1114): weighted value result of calculation
Go on foot meteorological factor weighted value
under this sight of acquisition through above four:
The meteorological factor weighted value of table 2 in polluting rising and decline sight
| w1i | Temperature | The proxima luce (prox. luc) temperature | Air pressure | Proxima luce (prox. luc) air pressure | Wind speed | The proxima luce (prox. luc) wind speed | Wind direction |
| PM10 | 0.01 | 0.05 | 0.01 | 0.03 | 0.20 | 0.02 | 0.02 |
| w1i | The proxima luce (prox. luc) wind direction | Solar radiation | The proxima luce (prox. luc) solar radiation | Rainfall amount | The proxima luce (prox. luc) rainfall amount | Humidity | Proxima luce (prox. luc) humidity |
| PM10 | 0.15 | 0.06 | 0.08 | 0.11 | 0.12 | 0.06 | 0.10 |
(112): the analysis in seriously polluted and slight period
(1121): the meteorological factor typical value is calculated as follows:
Table 3 meteorological factor typical value
(1122): numerical value normalization is calculated
(1123): the meteorological factor change degree calculates
(1124): weighted value result of calculation
Go on foot meteorological factor weighted value
under this sight of acquisition through above four:
The meteorological factor weighted value of table 4 in seriously polluted and slight scenario analysis
| w2i | Temperature | The proxima luce (prox. luc) temperature | Air pressure | Proxima luce (prox. luc) air pressure | Wind speed | The proxima luce (prox. luc) wind speed | Wind direction |
| PM10 | 0.01 | 0.01 | 0.02 | 0.04 | 0.13 | 0.11 | 0.03 |
| w2i | The proxima luce (prox. luc) wind direction | Solar radiation | The proxima luce (prox. luc) solar radiation | Rainfall amount | The proxima luce (prox. luc) rainfall amount | Humidity | Proxima luce (prox. luc) humidity |
| PM10 | 0.01 | 0.03 | 0.04 | 0.34 | 0.17 | 0.03 | 0.03 |
(113): related coefficient result of calculation
Table 5 pollutant levels and meteorological factor related coefficient
| Related coefficient | Temperature | The proxima luce (prox. luc) temperature | Air pressure | Proxima luce (prox. luc) air pressure | Wind speed | The proxima luce (prox. luc) wind speed | Wind direction |
| PM10 | -0.09 | -0.19 | 0.30 | 0.39 | -0.42 | -0.42 | 0.01 |
| Related coefficient | The proxima luce (prox. luc) wind direction | Solar radiation | The proxima luce (prox. luc) solar radiation | Rainfall amount | The proxima luce (prox. luc) rainfall amount | Humidity | Proxima luce (prox. luc) humidity |
| PM10 | 0.07 | 0.05 | 0.09 | 0.04 | 0.05 | -0.27 | -0.37 |
(114): confirm weight matrix
Carry out the screening of influence factor and the correction of weight through overtesting, set up the weight matrix that sample is optimized at last.
Table 6 sample is optimized weight matrix
(12): the confirming of threshold matrix
(121): the best of clear and definite experiment purpose-find out sample optimization makes up with it; Confirm experimental index--with forecast model absolute error AE as test index.
(122): select factor, decide level.Result according to weight matrix confirms four experimental factors: wind, relative humidity, rainfall grade, air pressure, be the nonlinear relationship of investigation factor and PM10 error prediction model, and respectively select three levels.As shown in table 7.
Table 7 factor level table
(123): selected orthogonal table, design gauge outfit.The orthogonal table of selecting for use is L9 (34), and four factors are arranged in A, B, C, D four respectively and list.
(124): level translation, establishment experimental program.Do 9 tests altogether, testing program is as shown in table 8.
(125): make an experiment by scheme, record test index end value is seen table 8 " model AE " row, and experimental result is analyzed.Process and result are as shown in table 8, calculate
value.
As; The value of K I first row represent under the first row factor (A wind) the I level pairing test index with; Be 0.0127+0.0119+0.0128=0.0374; The value of K III the 2nd row represent under secondary series factor (B humidity) the II level pairing experimental index and, i.e. 0.0128+0.0126+0.0115=0.0369.And the like.
(126): the mean value
that calculates the same level of each factor.
(127): calculate the extreme difference
of each factor, according to the primary and secondary influence order of extreme difference decision factor.
(128): select excellent combination.Mean value
according to each factor level is confirmed excellent level.As for Elements C (rainfall grade), < < the k III is so optimal level is an II to the k I to have the k II.And the like, the final optimum combination of confirming is an A III B III C II D I.
Table 8 is optimized threshold value to the sample of PM10 forecast model and is selected testing program and interpretation of result
Wherein the proxima luce (prox. luc) threshold value increases on the basis of experimental result to some extent, and except that the rainfall grade increases 1, all the other parameters all increase by 2.Setting the population sample threshold value is 5.Set up the threshold matrix that sample is optimized thus, as shown in table 9.
Table 9 sample is optimized threshold matrix
(13): the confirming of sample size
Test with different sample sizes, obtaining sample size is that 330 o'clock precision are the highest, is 330 so confirm to be used for training the sample size of PM10 neural network.
(2) sample optimization screening
(21): according to the method for step 21 sample is carried out ground floor optimization screening, promptly filter out each meteorologic factor (today wind, rainfall today, rainfall yesterday, yesterday air pressure, yesterday humidity) similarity and all reach the sample of (seeing table 9) in the given threshold range.
(22): according to the method for step 22 the initial sample subclass that obtained in the last step is carried out second layer optimization screening, promptly filter out the sample that overall meteorological similarity reaches in the defined threshold scope (≤5).
(23): it is the ascending order arrangement of order standard that the double optimization sample subclass that obtained in the last step is carried out with s; Get sample sequence Q,, then all keep if sample number is less than 330; If more than 330, then filter out and predict day the highest preceding 330 samples of meteorological background similarity.
So far, accomplish whole work of screening sample.
Claims (10)
1. the sample optimization method towards prediction of air quality is characterized in that, may further comprise the steps:
(1) confirm the correlation parameter of sample optimization screening, its specifically:
(11) adopt pollutant levels and meteorological factor analysis by synthesis method, confirm the meteorological factor weight matrix, its specifically:
(111) obtain meteorological factor weighted value under the pollutant rise and fall sight;
(112) obtain meteorological factor weighted value under the serious and slight sight of pollutant;
(113) related coefficient of calculating pollutant quality concentration and meteorological factor;
(114) calculate the initial weight value of each meteorological factor, set up weight matrix;
(12) adopt orthogonal experiment method to confirm threshold matrix;
(13) adopt the method for experimental check to confirm sample size;
(2) filter out the sample of optimization, it is specially:
(21) filter out each meteorological similarity and reach the sample in the threshold range;
(22) filter out overall meteorological similarity and reach the sample in the threshold range;
(23) filter out and predict day the highest sample of meteorological background similarity.
2. the sample optimization method towards prediction of air quality according to claim 1 is characterized in that, the concrete steps of said step (111) are:
(1111) obtain sight meteorological factor representative data once; The up-down value that is pollutant concentration today and concentration contrast yesterday respectively more than 0.05mg/m3 and-average and maximal value, minimum value and the mean value of analyzing this meteorological factor in the period of interim each meteorological factor during below the 0.05mg/m3 two; Be upward period mean value
, downward period mean value
and maximal value
, minimum value
and the mean value
of analyzing the period, wherein
is the meteorological factor label;
(1112) numerical value normalization is handled, and the utilization following formula is handled,
，
，
；
(1113) calculate meteorological factor change degree,
;
(1114) calculate weighted value;
; Wherein
is the meteorological factor change degree, and
is the meteorological factor species number.
3. the sample optimization method towards prediction of air quality according to claim 1 is characterized in that, the concrete steps of said step (112) are:
(1121) obtain two times meteorological factor representative datas of sight; The API value that is pollutant is maximal value, minimum value and the mean value of this meteorological factor in the average of each meteorological factor more than 100 and in two periods below 20 and analysis period respectively; Be seriously polluted mean value in period
, pollute slight mean value in period
and maximal value
, minimum value
and the mean value
of analysis period, wherein
is the meteorological factor label;
(1122) numerical value normalization is handled, and the utilization following formula is handled,
(1123) calculate meteorological factor change degree,
;
(1124) calculate weighted value;
; Wherein
is the meteorological factor change degree, and
is the meteorological factor species number.
4. the sample optimization method towards prediction of air quality according to claim 1 is characterized in that, the related coefficient of pollutant quality concentration and meteorological factor is described in the said step (113):
5. the sample optimization method towards prediction of air quality according to claim 1 is characterized in that, the initial weight value of each meteorological factor is described in the said step (114):
Where,
is the correlation coefficient;
and
, respectively under scenario one and scenario two weight values calculated.
6. the sample optimization method towards prediction of air quality according to claim 1 is characterized in that, the concrete steps of step (12) are:
(121) confirm that experimental index is model prediction result's a absolute error value;
(122) select factor, decide level, need to confirm the experimental factor investigated according to the result of S1 step weight matrix, in this patent, promptly choose the big meteorologic factor of pollutant levels weighing factor value as experimental factor, and draft the level of each factor;
(123) design the orthogonal table gauge outfit, experimental factor is filled into the row of orthogonal table respectively;
(124) insert each level numeral the row of orthogonal table;
(125) value of calculating
, wherein
be
row factor
pairing test index of level with;
(126) calculate the mean value
of the same level of each factor;
is the mean value of
(127) calculate the extreme difference
of each factor
，
(128) optimal combination is confirmed excellent level according to the mean value
of each factor level.
7. the sample optimization method towards prediction of air quality according to claim 6 is characterized in that, the factor number should be not more than the columns of orthogonal table in the step (123).
8. the sample optimization method towards prediction of air quality according to claim 1; It is characterized in that; The method of definite employing experimental check of said step (13) sample size adopts a plurality of sample sizes to make an experiment respectively to every kind of pollutant, chooses a highest sample size of precision of prediction.
9. the sample optimization method towards prediction of air quality according to claim 1 is characterized in that, the screening mechanism of said step (2) Screening Samples is similar with meteorology to be criterion, and the concrete steps of said step (2) are:
(21) filter out each meteorological similarity and reach the sample in the threshold range, concrete grammar is:
Sample must satisfy following formula:
; Wherein,
In the formula,
is the prediction meteorological factor value of day;
(22) filter out overall meteorological similarity and reach the sample in certain threshold range, the sample that filters out must satisfy following formula:
In the formula,
is overall meteorological similarity;
is the threshold value of overall meteorological similarity screening;
(23) filter out and predict day the highest
bar sample of meteorological background similarity, the sample that filters out must satisfy following formula:
In the formula,
is the ascending order sample row with overall meteorological similarity
ordering;
10. according to each described sample optimization method of claim 1-9, it is characterized in that said meteorological factor is temperature, air pressure, wind speed, wind direction, solar radiation, rainfall amount or relative humidity towards prediction of air quality.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210228817.5A CN102799772B (en) | 2012-07-03 | 2012-07-03 | Towards the sample optimization method of prediction of air quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210228817.5A CN102799772B (en) | 2012-07-03 | 2012-07-03 | Towards the sample optimization method of prediction of air quality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102799772A true CN102799772A (en) | 2012-11-28 |
| CN102799772B CN102799772B (en) | 2015-09-30 |
Family
ID=47198880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210228817.5A Active CN102799772B (en) | 2012-07-03 | 2012-07-03 | Towards the sample optimization method of prediction of air quality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102799772B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103353923A (en) * | 2013-06-26 | 2013-10-16 | 中山大学 | Self-adaption spatial interpolation method and system based on spatial feature analysis |
| CN103472502A (en) * | 2013-09-18 | 2013-12-25 | 中山大学 | Method for dynamically showing regional air quality and meteorological field |
| CN104503404A (en) * | 2014-12-12 | 2015-04-08 | 广西瀚特信息产业股份有限公司 | Indoor air quality automatic regulating system based on environmental perception |
| CN104850734A (en) * | 2015-04-21 | 2015-08-19 | 武大吉奥信息技术有限公司 | Air quality index prediction method based on spatial and temporal distribution characteristics |
| CN107133636A (en) * | 2017-03-30 | 2017-09-05 | 宁波市水利水电规划设计研究院 | A kind of method and system for obtaining similar typhoon |
| CN107273995A (en) * | 2016-04-08 | 2017-10-20 | 株式会社日立制作所 | Urban Air Pollution Methods |
| CN107292417A (en) * | 2017-05-09 | 2017-10-24 | 北京市环境保护监测中心 | Region heavily contaminated based on heavily contaminated sequence case library differentiates forecasting procedure and device |
| CN107831699A (en) * | 2017-11-17 | 2018-03-23 | 广州矽创信息科技有限公司 | A kind of intelligent data acquisition analysis method and system |
| CN108280131A (en) * | 2017-12-22 | 2018-07-13 | 中山大学 | A kind of atmosphere pollution under meteorological effect changes relationship quantitative estimation method |
| CN110334732A (en) * | 2019-05-20 | 2019-10-15 | 北京思路创新科技有限公司 | A kind of Urban Air Pollution Methods and device based on machine learning |
| CN110378822A (en) * | 2019-05-22 | 2019-10-25 | 云南省大理白族自治州气象局 | A kind of optimal meteorological factor building screening technique influencing lake water quality |
| CN110795814A (en) * | 2019-08-27 | 2020-02-14 | 中国农业科学院农业环境与可持续发展研究所 | Optimization method for simulating watershed non-point source pollution interaction effect |
| CN111323847A (en) * | 2018-12-13 | 2020-06-23 | 北京金风慧能技术有限公司 | Method and apparatus for determining weight ratios for analog integration algorithms |
| CN111611296A (en) * | 2020-05-20 | 2020-09-01 | 中科三清科技有限公司 | PM2.5Pollution cause analysis method and device, electronic equipment and storage medium |
| US10830922B2 (en) | 2015-10-28 | 2020-11-10 | International Business Machines Corporation | Air quality forecast by adapting pollutant emission inventory |
| CN113051273A (en) * | 2021-03-30 | 2021-06-29 | 天津市生态环境科学研究院 | Air quality data processing method and device, electronic equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102301230A (en) * | 2008-12-19 | 2011-12-28 | 达维斯技术有限公司 | System and apparatus for measurement and mapping of pollutants |
-
2012
- 2012-07-03 CN CN201210228817.5A patent/CN102799772B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102301230A (en) * | 2008-12-19 | 2011-12-28 | 达维斯技术有限公司 | System and apparatus for measurement and mapping of pollutants |
Non-Patent Citations (3)
| Title |
|---|
| ATAKAN KURT等: "Forecasting air pollutant indicator levels with geographic model 3 days in advance using neural networks", 《EXPERT SYSTEMS WITH APPLICATIONS》, 31 December 2010 (2010-12-31), pages 7986 - 7992 * |
| LU LI等: "Urban air quality forecast system based on sample optimization and its application", 《THE WORLD CONGRESS ON COMPUTER SCIENCE AND INFORMATION ENGINEERING(CSIE)》 》, 19 June 2011 (2011-06-19), pages 163 - 169 * |
| 刘永红等: "基于BP神经网络的佛山空气质量预报模型的研究", 《安全与环境学报》, vol. 11, no. 2, 25 April 2011 (2011-04-25), pages 125 - 130 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103353923A (en) * | 2013-06-26 | 2013-10-16 | 中山大学 | Self-adaption spatial interpolation method and system based on spatial feature analysis |
| CN103353923B (en) * | 2013-06-26 | 2016-06-29 | 中山大学 | Adaptive space interpolation method and system thereof based on space characteristics analysis |
| CN103472502A (en) * | 2013-09-18 | 2013-12-25 | 中山大学 | Method for dynamically showing regional air quality and meteorological field |
| CN103472502B (en) * | 2013-09-18 | 2014-09-17 | 中山大学 | Method for dynamically showing regional air quality and meteorological field |
| CN104503404A (en) * | 2014-12-12 | 2015-04-08 | 广西瀚特信息产业股份有限公司 | Indoor air quality automatic regulating system based on environmental perception |
| CN104850734A (en) * | 2015-04-21 | 2015-08-19 | 武大吉奥信息技术有限公司 | Air quality index prediction method based on spatial and temporal distribution characteristics |
| CN104850734B (en) * | 2015-04-21 | 2017-09-15 | 武大吉奥信息技术有限公司 | A kind of air quality index Forecasting Methodology based on spatial-temporal distribution characteristic |
| US10830922B2 (en) | 2015-10-28 | 2020-11-10 | International Business Machines Corporation | Air quality forecast by adapting pollutant emission inventory |
| CN107273995A (en) * | 2016-04-08 | 2017-10-20 | 株式会社日立制作所 | Urban Air Pollution Methods |
| CN107133636A (en) * | 2017-03-30 | 2017-09-05 | 宁波市水利水电规划设计研究院 | A kind of method and system for obtaining similar typhoon |
| CN107133636B (en) * | 2017-03-30 | 2020-06-16 | 宁波市水利水电规划设计研究院有限公司 | Method and system for obtaining similar typhoons |
| CN107292417B (en) * | 2017-05-09 | 2020-03-17 | 北京市环境保护监测中心 | Regional heavy pollution discrimination and forecast method and device based on heavy pollution sequence case library |
| CN107292417A (en) * | 2017-05-09 | 2017-10-24 | 北京市环境保护监测中心 | Region heavily contaminated based on heavily contaminated sequence case library differentiates forecasting procedure and device |
| CN107831699A (en) * | 2017-11-17 | 2018-03-23 | 广州矽创信息科技有限公司 | A kind of intelligent data acquisition analysis method and system |
| CN108280131A (en) * | 2017-12-22 | 2018-07-13 | 中山大学 | A kind of atmosphere pollution under meteorological effect changes relationship quantitative estimation method |
| CN111323847A (en) * | 2018-12-13 | 2020-06-23 | 北京金风慧能技术有限公司 | Method and apparatus for determining weight ratios for analog integration algorithms |
| CN110334732A (en) * | 2019-05-20 | 2019-10-15 | 北京思路创新科技有限公司 | A kind of Urban Air Pollution Methods and device based on machine learning |
| CN110378822A (en) * | 2019-05-22 | 2019-10-25 | 云南省大理白族自治州气象局 | A kind of optimal meteorological factor building screening technique influencing lake water quality |
| CN110378822B (en) * | 2019-05-22 | 2023-04-07 | 云南省大理白族自治州气象局 | Optimal meteorological factor construction and screening method for influencing lake water quality |
| CN110795814A (en) * | 2019-08-27 | 2020-02-14 | 中国农业科学院农业环境与可持续发展研究所 | Optimization method for simulating watershed non-point source pollution interaction effect |
| CN111611296A (en) * | 2020-05-20 | 2020-09-01 | 中科三清科技有限公司 | PM2.5Pollution cause analysis method and device, electronic equipment and storage medium |
| CN111611296B (en) * | 2020-05-20 | 2021-02-19 | 中科三清科技有限公司 | PM2.5Pollution cause analysis method and device, electronic equipment and storage medium |
| CN113051273A (en) * | 2021-03-30 | 2021-06-29 | 天津市生态环境科学研究院 | Air quality data processing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102799772B (en) | 2015-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102799772A (en) | Air quality forecast oriented sample optimization method | |
| CN108876021B (en) | Medium-and-long-term runoff forecasting method and system | |
| CN102425148B (en) | Rapid sub-grade settlement predicting method based on static sounding and BP (Back Propagation) neural network | |
| US20160203245A1 (en) | Method for simulating wind field of extreme arid region based on wrf | |
| CN112465243B (en) | Air quality forecasting method and system | |
| CN111144055B (en) | Method, device and medium for determining concentration distribution of toxic heavy gas leakage in urban environment | |
| CN105740991A (en) | Climate change prediction method and system for fitting various climate modes based on modified BP neural network | |
| CN116205310B (en) | Soil water content influence factor sensitive interval judging method based on interpretable integrated learning model | |
| CN109143408B (en) | Dynamic region combined short-time rainfall forecasting method based on MLP | |
| CN106815473B (en) | Hydrological simulation Uncertainty Analysis Method and device | |
| CN110658307A (en) | Method for evaluating influence of pollution source on environmental air quality | |
| CN108171007A (en) | One kind is based on the modified Medium-and Long-Term Runoff Forecasting method of numerical value DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM extreme value | |
| CN111784065B (en) | Oil well productivity intelligent prediction method based on grey correlation | |
| CN115526108B (en) | Landslide stability intelligent dynamic prediction method based on multisource monitoring data | |
| CN104915982A (en) | Canopy layer illumination distribution prediction model construction method and illumination distribution detection method | |
| CN111639803A (en) | Prediction method applied to future vegetation index of area under climate change scene | |
| CN115730852A (en) | Chemical enterprise soil pollution control method and system | |
| CN114882361A (en) | Deep learning forest overground biological estimation method based on multi-source remote sensing fusion | |
| CN113486295A (en) | Fourier series-based total ozone change prediction method | |
| CN111914488B (en) | Data area hydrologic parameter calibration method based on antagonistic neural network | |
| CN116227692B (en) | Crop heavy metal enrichment risk quantification method, system and storable medium | |
| CN116757321A (en) | Solar direct radiation quantity prediction method, system, equipment and storage medium | |
| CN111126827A (en) | Input-output accounting model construction method based on BP artificial neural network | |
| CN110648023A (en) | Method for establishing data prediction model based on quadratic exponential smoothing improved GM (1,1) | |
| CN114254802B (en) | Prediction method for vegetation coverage space-time change under climate change drive |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180124 Address after: 510275 Guangdong Guangzhou City, Guangzhou, Haizhuqu District, Xingang West Road, No. 135 big science and technology complex building B self - made room 1614 Patentee after: Guangzhou Zhongda Holding Co., Ltd. Address before: 510275 Xingang West Road, Guangdong, China, No. 135, No. Patentee before: Sun Yat-sen University |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20180211 Address after: 510275 Guangdong Guangzhou City, Guangzhou, Haizhuqu District, Xingang West Road, No. 135 big science and technology complex building B self - made room 1614 Patentee after: GUANGZHOU ZHONG DA INDUSTRY GROUP CO., LTD. Address before: 510275 Guangdong Guangzhou City, Guangzhou, Haizhuqu District, Xingang West Road, No. 135 big science and technology complex building B self - made room 1614 Patentee before: Guangzhou Zhongda Holding Co., Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180322 Address after: 510275 self numbered 411B room A of the 628 Zhongda Science Park building in Dapu Garden District, Guangzhou Xingang West Road, Haizhuqu District, Guangdong Patentee after: Guangdong Fundway Technology Co., Ltd. Address before: 510275 Guangdong Guangzhou City, Guangzhou, Haizhuqu District, Xingang West Road, No. 135 big science and technology complex building B self - made room 1614 Patentee before: GUANGZHOU ZHONG DA INDUSTRY GROUP CO., LTD. |
|
| TR01 | Transfer of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Sample optimization method for air quality prediction Effective date of registration: 20201116 Granted publication date: 20150930 Pledgee: Bank of China Limited Dongshan Branch of Guangzhou Pledgor: GUANGDONG FUNDWAY TECHNOLOGY Co.,Ltd. Registration number: Y2020440000361 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |