CN112513896A - Method for predicting atmospheric pollution - Google Patents

Method for predicting atmospheric pollution Download PDF

Info

Publication number
CN112513896A
CN112513896A CN201980006136.4A CN201980006136A CN112513896A CN 112513896 A CN112513896 A CN 112513896A CN 201980006136 A CN201980006136 A CN 201980006136A CN 112513896 A CN112513896 A CN 112513896A
Authority
CN
China
Prior art keywords
air quality
data
grid
time
historical
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
Application number
CN201980006136.4A
Other languages
Chinese (zh)
Other versions
CN112513896B (en
Inventor
宋江山
刘一平
张子珺
高健
司书春
何新
许军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chinese Research Academy of Environmental Sciences
Nova Fitness Co Ltd
Original Assignee
Chinese Research Academy of Environmental Sciences
Nova Fitness Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chinese Research Academy of Environmental Sciences, Nova Fitness Co Ltd filed Critical Chinese Research Academy of Environmental Sciences
Publication of CN112513896A publication Critical patent/CN112513896A/en
Application granted granted Critical
Publication of CN112513896B publication Critical patent/CN112513896B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Air Conditioning Control Device (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Testing Or Calibration Of Command Recording Devices (AREA)

Abstract

A prediction method of environmental pollution belongs to the field of environmental monitoring. Vectorization analysis is carried out on data of a gridding database by establishing a three-dimensional space-time grid to obtain characteristic vectors of all or part of data units; and predicting the value of the data unit of the future period by using the characteristic vector of the data unit of a period of time after the similar grid interval.

Description

Method for predicting atmospheric pollution
The invention relates to a prediction method of environmental pollution, belonging to the field of environmental monitoring. In the industrial process, human beings have serious damage to the natural environment, various pollutions are generated, and the atmospheric pollution is one of the main pollutions. Air pollution directly endangers people's health, so people have a need to be able to know the air quality at a more accurate future date in order to arrange their work and life, and this need is strong. Air quality data generally comes mainly from measured values of environmental protection departments. The existing technologies also include technologies for predicting air quality, which are mainly divided into two types: one method is to forecast based on chemical forecasting model calculation, namely, to establish a diffusion model, and to forecast based on chemical forecasting model calculation, which needs extremely high calculation resources and is difficult to realize; the other method is to predict the air quality data at the local prediction time based on local historical meteorological data and historical air quality data and combining with meteorological data at the prediction time, and when the air quality data at the local prediction time is predicted, the selected historical meteorological data and the selected historical air quality data are data at the same time as the prediction time in the historical time, for example, the prediction time is 15:00, and the selected historical meteorological data and the selected historical air quality data are data at a certain date or dates of 15:00 in the history, and the accuracy of the air quality data predicted by adopting the method is low. The two air quality prediction modes have many disadvantages, the first mode needs a large amount of parameter data input and has extremely high requirements on computing resources and a meteorological monitoring network; the second method is based on historical meteorological data and historical air quality data, needs two kinds of data at the same time, and the simple prediction method based on the historical meteorological data and the historical air quality data has low accuracy. Both methods require meteorological data and cannot accurately predict medium and small scales in real time; the moving direction and trajectory of the pollution drift cannot be accurately predicted. There have been some studies on the prediction of contaminants by relevant personnel. Chinese patent application No.: 201510287229.2, title of the invention: a method and apparatus for predicting air quality. The method selects certain historical meteorological data and historical air quality data from historical meteorological data and historical air quality data of all regions within a prediction region and a preset distance range around the prediction region, uses the data, current meteorological data and air quality data as input parameters, and inputs a function to predict the air quality. The invention still requires meteorological data and cannot predict the path and trend of pollutant drift. Chinese patent application No.: 201710818682.0, title of the invention: an air quality prediction method and device. The method utilizes the historical data of the air quality and the target time, and predicts simply by analyzing the probability of the possible air condition of the historical air quality in the target time. The lack of use of existing monitoring data at all results in a significant reduction in prediction accuracy and a high probability of a prediction not matching the current situation. Summary of the invention terminology
1. Historical air quality data: air contaminant concentrations at a certain time of history.
2. Historical air quality data characteristics: and during a certain two historical moments, expressing the vector of the contribution of the previous moment of the monitored area to the pollutants in the surrounding area at the later moment.
3. Historical air quality data feature library: a database consisting of vectors characterizing historical air quality data.
4. Air quality data frame: the method comprises the steps of dividing an area to be predicted into grids with set density according to prediction requirements, giving historical air quality data into the grids according to time and geographic positions, and generating an air quality data set with geographic position information based on time series.
5. Air quality data matrix: and expressing the data contained in the data frame in a matrix form to obtain a matrix, namely the air quality data matrix.
6. Recent air quality data: and air quality data obtained by statistics before the pollution process to be predicted is compared with the historical data.
7. Recent air quality data characteristics: and expressing the vector of the contribution of the previous moment of the monitored area to the pollutants in the surrounding area at the later moment between the moment when the pollution process to be predicted is cut off and the moment before the comparison with the historical data is carried out.
8. Matching degree coefficient: and the coefficient represents the matching degree of the recent air quality data characteristic of the pollution process to be predicted and the historical air quality data characteristic to be matched.
9. Vector group: and calculating a vector group containing a characteristic vector characterization pollutant diffusion path in each grid according to the air quality data frames at the two moments.
10. Time-to-time air quality data characteristics: and characterizing the vector of pollutant diffusion information between two moments. The method aims to overcome the defect that the air quality prediction in the prior art requires high requirements on computing resources by meteorological parameters such as wind speed and wind direction, or the defect of simple probability prediction by means of historical data in the prior art. The invention provides an air quality prediction method, which can accurately predict air pollution and pollution drift path trend under the conditions of utilizing less computing resources and not using near-surface meteorological data which is not easy to obtain. In order to achieve the purpose, the invention provides the following technical scheme:
1. a method for predicting atmospheric pollution comprises the following steps:
1) establishing a historical air quality database: the historical air quality database comprises historical air quality data acquired by various air quality monitoring devices; the historical air quality data comprises two-dimensional geographic position information and time stamp information;
2) establishing a three-dimensional space-time grid: the three-dimensional space-time grid takes a two-dimensional geographic position and time as an axis;
3) establishing a gridding database: generating a unique data unit in each grid; the data cells are calculated from historical air quality data falling into the grid; or derived from neighboring grids of the grid;
4) vectorizing analysis is carried out on the data of the gridding database to obtain the characteristic vectors of all or part of data units;
5) comparing and matching the characteristics of the data units in the gridding database at the current period of time with the data units in the gridding database at the non-current period of time; obtaining one or more similar grid intervals with the highest matching degree;
6) and predicting the value of the data unit in the future period by using the characteristic vector of the data unit in a period after the similar grid interval. Establishing a historical air quality database to obtain information such as historical air quality data, geographical position information, an area to be predicted and the like, and establishing the historical air quality database, wherein the specific method comprises the following steps: determining a geographical area range of an area to be predicted; historical air quality data with geographical position information in the area range to be predicted are obtained, and the historical air quality data with the geographical position information can be data collected by a state control station, a super station, an air quality monitoring micro station, a mobile station and the like. Establishing a gridding database, dividing the area to be predicted into grids with set density according to prediction requirements, giving historical air quality data into the grids according to time and geographic positions, and generating air quality data frames with two-dimensional geographic position information and time stamp information. And establishing a three-dimensional space-time grid by taking the time information as an axis, and arranging data frames with two-dimensional geographic position information and air quality data to generate the three-dimensional space-time grid. The method for endowing air quality with geographical position information and time stamp information in the grid comprises the following steps:
1) only one air quality information falls into one grid at the same time, and the air quality data of the grid is the one air quality information.
2) A plurality of air quality information fall into a grid in the same time, and the air quality data of the grid is the average value of the air quality information.
3) And the grid with no air quality information falling into the grid can be obtained by performing mathematical methods such as interpolation, diffusion model and the like on grid data of adjacent spaces at the same time.
4) The grid with no air quality information falling into can also be obtained by interpolation, diffusion model and other mathematical methods through the grid data of the same space and adjacent moments.
5) The side length of each two-dimensional geographic grid may be 10 meters to 1000 meters.
6) The same time point refers to air quality data 1 minute-1 hour before and after the time point. Analyzing the characteristics of a historical air quality database by a vectorization analysis gridding database, analyzing the characteristics of the historical air quality database, and analyzing an air quality data frame with geographical position information. The method for obtaining the air quality data matrix comprises the following steps: and filling the historical air quality data at the moment into the divided grids according to the geographical position information to obtain a 7\ moment air quality data frame. The data frame is an air quality data plane with two-dimensional geographic position information at one moment in a three-dimensional space-time network.
Figure IMGF000007_0003
Converting the 7\ moment air quality data frame into an A matrix according to grids, wherein the first row and the first column in the A matrixThe value of the element(s) is the air quality of the row one and the column one in the Ti moment air quality data privet, and so on, the value of the element(s) in the row m and the column n in the a matrix is the air quality of the row m and the column n in the moment air quality data frame, and the a matrix represents the 7\ moment regional air quality data frame.
Figure IMGF000007_0001
The time B air quality data matrix is obtained by the method similarly, and the B matrix represents the air quality data frames in the 7 time region.
Figure IMGF000007_0004
Figure IMGF000007_0002
The method for obtaining the historical air quality data characteristics comprises the following steps: and respectively calculating the pollution contribution of each grid to the adjacent grid at the next moment in the previous moment, wherein the pollution contribution of each grid to the adjacent grid is obtained in a vector calculation mode.
Figure IMGF000008_0004
Obtaining an analysis matrix
Figure IMGF000008_0001
The data is the air quality data of the previous moment, and ^ is the air quality data of the next moment. In the above, I is the air quality data at the previous moment, T2Air quality data at the latter time.
Figure IMGF000008_0002
^mnB(m+iXn+l) ,Pollution drift vector calculation methodThe following were used:
Figure IMGF000008_0003
Figure IMGF000009_0001
·^mn^(m+l)(n+l)
Figure IMGF000009_0002
the contribution to the periphery is the direction of the drift of the pollution between these two moments, i.e. the
Figure IMGF000009_0003
Air quality data characteristics between time and time ^ a; the continuous characteristic at a plurality of time points can represent the drift path of the pollutant. Respectively calculating the time from 7\ to r of each area in the grid2Vector of time get, 7\ time to r2The vector group of the time is the characteristic of the pollution condition between the two time; and respectively calculating pollutant vector groups at all times in the historical air quality data to obtain the air quality historical data characteristics in the historical time period. And storing the historical air quality data characteristics in a file to obtain a historical air quality data characteristic database. The pollution drift vector is also referred to herein as a feature vector. Analyzing recent air quality data characteristics the method of analyzing recent air quality data characteristics is similar to the way of building a historical air quality data characteristics library. Firstly, assigning air quality data with geographical position information of an air quality monitoring station to grids divided in an area to be predicted, generating a current air quality data frame and one or more groups of data frames which are forward by a certain time by taking the current time as a reference, and further generating an air quality data matrix of the current air quality and the forward certain time. Method for obtaining established historical air quality data characteristics and air by using established historical air quality data characteristics databaseThe quality data matrix obtaining method can obtain the vector group of recent air quality data change, and the vector group is the recent air quality data characteristic.
Figure IMGF000010_0003
Figure IMGF000010_0001
The effect of the area on the current air quality over time, continuous characterization over multiple time instants can represent the recent pollutant f wind shift path. After the characteristic of the recent air quality data is determined by the matching method of the feature vectors of the recent air quality data and the historical air quality data, the characteristic of the recent air quality data is compared with the characteristic of the historical air quality data to obtain a matching coefficient T1. According to mathematical methods such as the shortest vector distance, the cosine of an included angle, the Mahalanobis distance, the vector similarity and the like, the historical air quality data characteristics closest to the recent air quality data characteristics can be found, and the historical air quality motion process or the pollution process closest to the current air quality or the current pollution condition and the motion path is also found. During the matching process, other influencing factors should be considered/as follows: setting a factor temperaturetTemperature influence factor (factor humidity):
Figure IMGF000010_0002
seasonal influencing factor (factor sector)5. If the historical air quality data and the recent air quality data are close to or the same in season and temperature and humidity, the matching degree is high; if the season and the temperature and humidity difference between the historical air quality data and the recent air quality data are large, the influence factor value is small. Setting an extreme weather influencing factor (factor weather):w. Extreme weather exists between the historical air quality data and the recent air quality data, the value of an extreme weather influence factor is very low, the data cannot be used as prediction reference at that time, and the current situation is also not suitableAnd (5) predicting. Setting a path influencing factor (factor path) < >p. In the historical air quality data and the recent air quality data, the distance of the pollution moving path and the pollution source should be considered. If the recent air quality data characteristic has a higher matching degree with the pollutant drift paths of the plurality of historical air quality data characteristics, the historical air quality data characteristic path which is closer to the path in the recent air quality data characteristic has a higher matching degree. Setting a factor influencing the degree of diffusion (factor differentiation) < >d. In the case of similar contaminant diffusion paths, the degree of diffusion of the two contamination processes should be taken as a parameter. If the diffusion degrees and the area level of the influence ranges of the two pollution processes are similar, the matching degree coefficient should be correspondingly increased, and if the diffusion degrees and the area level of the influence ranges of the two pollution processes are relatively different, the matching degree coefficient should be correspondingly reduced; setting a factor repeatability affecting factor (factor repeatability)r. The number of times a historical similar contamination process occurs should be a parameter. If the similar historical pollution process model matched with the pollution process to be predicted occurs for many times, the reliability of prediction performed by using the historical air quality data is considered to be high, and a high matching degree coefficient is set; a terrain influencing factor (factor geo) is set. Historical and topographical factors at the site of production of the contamination process to be predicted should also be taken as parameters. If the terrain produced by two pollution processes differs greatly, for example, if there are not many buildings in place several years ago, and if there are many buildings in the past, the matching degree coefficient of the buildings not found several years ago is reduced accordingly. Other impact factor determination methods table:
Figure IMGF000011_0001
the method for matching cosine of included angle comprises the following steps: comparing the recent air quality data characteristics with the historical air quality data is required for performing characteristic comparison matching, namely
Figure IMGF000012_0001
And (6) carrying out comparison. the matching coefficient of the angle cosine method is applied to the mth row and the nth column of squares at the moment t
Figure IMGF000012_0002
:
Figure IMGF000012_0003
Cosine similarity measures the difference between two individuals by using the cosine value of the included angle between two vectors in the vector space. The closer the cosine value is to 1, the closer the angle is to 0 degrees. Similarly, the comparison of the vectors ^ and ^ representing the recent and historical air quality characteristics of the monitored area at a specific moment can be completed by an included angle cosine method, and the calculation process is as above (note: all air quality data obtained by the monitored period, an included angle cosine method matching coefficient rf is applied in the whole grid range at the moment t:
Figure IMGF000012_0004
applying matching coefficient of included angle cosine method to mth row and nth column of squares at certain moment in period T
Figure IMGF000012_0005
q represents the number of matches made over a period of T:
Figure IMGF000012_0006
applying a matching coefficient rf of an included angle cosine method in the whole grid range in a period T, wherein q represents the matching times in the period T: iiT = - 2L
q takes other influence factors into consideration, and the correction formula of the matching coefficient is as follows: r \f = f x r\
T ]' is that the closer the matching coefficient of the corrected matching coefficient is to 1, the better the matching performance is, the more similar the current characteristic is to a certain section of characteristic of the historical air quality data characteristic library, the higher the possibility of future occurrence is; the closer the matching coefficient is to 0, the poorer the matching, and the less similar the current feature is to a certain segment of the historical air quality data feature library, which is about impossible to happen.
Figure IMGF000013_0001
The data unit matching method compares the recent air quality data unit with the historical air quality data unit, finds the historical air quality data frame which is closest to the selected recent air quality data frame or is amplified or reduced in a certain proportion according to each data in the recent air quality data frame, and also finds the historical air quality motion process or the pollution process which is closest to the current air quality or the current pollution condition and the motion path. Examples of recent matches to historical air quality data: there are the following historical air quality data frame a and recent air quality data frame a. Now, the two data frames are compared to determine whether the historical contamination process of the data frame a can predict the development trend of the recent contamination process.
Figure IMGF000013_0002
A data frame
Figure IMGF000014_0003
A data frame
Figure IMGF000014_0001
Firstly, selecting single data in recent data frame and historical corresponding geographic position data to calculate to obtain a ratio 811-AfSimilarly, obtaining all grid data in the area
Figure IMGF000014_0002
And then based on the mean valueThe mode, the data distribution,
^11 ^mn
linear regression and other mathematical methods to count stool and urine L meeting set requirements
Figure IMGF000014_0004
A-A. Contrast noodle&As an example of the average value method, the S range satisfying the requirement is defined as 6 ± 0, 25. The value is defined as a similarity coefficient, and a is a specific value of the S-content comparison noodle corresponding to a predetermined range. If A is more than 80%, the data link glossy privet is considered to be similar to the data link glossy privet. Reflecting the prediction accuracy, the higher the prediction accuracy, can be adjusted according to the prediction accuracy. And a.. set less amount
Data frame ztmm: like 0
(similarly, t > K)
And K is a similarity parameter K = 0.8, 0.9, predicting future air quality based on a matching result and the current air quality situation, and after one or more similar grid intervals with the highest matching degree are obtained, calculating future air quality data by reversely applying a pollution drift vector calculation method to calculate and predict the future air quality data by taking the current air quality data as a reference (the current air quality data are known) and a pollution drift vector at a subsequent moment of the known historical matching grid moment (the pollution drift vector calculation method at the subsequent moment is still a pollution drift vector calculation method), so as to obtain the future air quality data. Description of the drawings fig. 1 is a schematic view of an air quality prediction process; FIG. 2 shows vector AnnB schematic diagram, FIG. 3 is from 7\ time to 72Historical air quality data feature vector schematic; FIG. 4 is a diagram of a vector ^ s; FIG. 5 is a graph of air quality data characteristics per grid from time 10:40 to time 10: 50; FIG. 6 is a characteristic diagram of air quality data in the area to be measured from time 10:40 to time 10: 50; FIG. 7 is a schematic diagram of the angle 0 between i and ^ i.
The embodiment of the present invention is based on the predicted regionA subway station in south City is the center, the periphery is 150m by 150m, and the area is 22500m2The pollution process of the square area of (1, 23) in 2019 continues from 9 am in 23 of 2019 to 5 pm in 23 of 1, 23 in 2019, and air quality data frames of 10: 40-10: 50 in the morning are taken to be monitored and analyzed in a pollutant drift path mode, and the resolution of the air quality data frames is 50M x 50M. Dividing the region into grids by taking 50M by 50M as a unit, wherein the region of Bei II contains 9 grids, and taking the grid at the lower left corner as an example to analyze the drift path of the pollutants. And filling the historical air quality data of the 1/23/2019 at the 10:40 and 10:50 am in divided grids according to the geographic position information to obtain an air quality data frame at the 10:40 moment and an air quality data frame at the 10:50 moment. The geographic position of the air pollution data is not continuous frequently, and the air quality data in the grid without the data can be obtained by utilizing mathematical algorithms such as interpolation and the like according to the existing air quality data, so that the pollution statistical data (PM) at 10:40 and 10:50 in the morning of 1 month and 23 days of 2019 are finally obtained (PM)2 SConcentration values) are as given in the table below
10:40 air quality data sheet
Figure IMGF000016_0001
10:50 air quality data table
Figure IMGF000016_0002
Converting the air quality data privet at the time of 10:40 into an A matrix according to grids, wherein the value of pi elements in the first row and the first column in the A matrix is the air quality in the first row and the first column in the data frame at the time of 10:40, the value of the element in the mth row and the nth column in the A matrix is the air quality in the mth row and the nth column in the data frame at the time of 10:40, and the A matrix represents a pollution degree data frame in a 10:40 time area. Similarly, the polluted data frame at the time of 10:50 is converted into a B matrix.
100 75 50
A = 135 110 85
170 145 120
Figure IMGF000017_0001
150 135 120
B = 165 150 135
180 165 150
And respectively calculating pollution contribution of each grid at the time of 10:40 to an adjacent grid at the time of 10:50, wherein the pollution contribution of each grid to the adjacent grid is obtained by a vector calculation mode. The following table:
Figure IMGF000017_0002
numbering two grid areas of 10:40 and 10:50 according to a numbering rule (taking a top left corner vertex of a grid at the top left corner of the grid area as an origin, taking the top left corner vertex as an X-axis, taking the top left corner vertex as a y-axis, establishing a coordinate grid for the y-axis longitudinally (in order to ensure that the grid numbering direction is consistent with the matrix arrangement direction, the y-axis is downward in the forward direction), numbering the grid according to the arrangement order of the grid in the X-axis and y-axis directions):
10:40 moment air quality coordinate grid
Figure IMGF000017_0003
Figure IMGF000018_0004
10:50 moment air quality coordinate grid
Figure IMGF000018_0005
Then the lower left hand corner grid area at time 10:40 contributes to the ten thousand dye in the area around time 10:50
Figure IMGF000018_0001
、 -<431^22' 31^32, the vector calculation method is as follows:
Figure IMGF000018_0002
engraving;Lregional contamination spread information. FIG. 4 is a vector diagram. The vector, A ^ B A ^ B A ^ B A ^ B A ^ B, is calculated respectively in the same ways A^B sThe calculations are performed separately and fig. 5 shows the vectors described above, which are characteristic of the air quality data for each grid.
Figure IMGF000018_0003
And obtaining a vector value from the moment to the 10:50 moment according to the air quality historical data characteristic. Air quality data characteristic of the time zone of 10:40 to 10: 50. After the recent air quality data characteristics of the predicted area are determined, comparing the air quality data characteristics with historical air quality data characteristics in a database, finding out the historical air quality data characteristics closest to the recent air quality data characteristics, after finding out the matched historical air quality data characteristics, inputting by taking the current air quality data as basic data, and performing vector operation and fitting, namely predicting the future air quality. The current moment is 8:00 in 28 months in 2019, and the air pollution situation in 8:10 in 28 months in 2019 is analyzed and predicted by an embodiment of predicting pollutants by using a grid at the lower left corner. The first step of prediction is to compare the recent vector with the historical vector, and according to the historical air quality data characteristic library, the air quality data characteristic = (25, 25) at the historical same-period time is obtained. By using the same calculation mode, the air quality data characteristics between 1 month and 28 days of 2019 and 07:50 and between 1 month and 28 months of 2019 and 8:00 are obtained.
Figure IMGF000019_0001
24) And comparing with ^ a. According to the cosine formula of the included angle:
Figure IMGF000019_0002
Figure IMGF000019_0003
0.9998^1, so the two vectors are considered to have extremely high matching degree, the historical data can be used for predicting pollutants, and the air quality data characteristics ^31 ^' = (26, 26) between the time of the next 10-minute gradient and the matched historical air quality data are known, wherein the components of the vectors are information
Figure IMGF000019_0004
20)， A31B2I ' = (0, 6) ,
A^BT2' = (6, 0), and the 08: 00 time B is known from monitoring data31The pollutant concentration of the grids is 180, and the pollution concentration of each grid of 11: 00 is B predicted by Bei 1J according to the information22=160 , B21=174 , B32=174。
8:10 air pollution condition prediction results around the lower left grid:
Figure IMGF000020_0001

Claims (1)

  1. claims
    1. A method for predicting atmospheric pollution comprises the following steps:
    1) establishing a historical air quality database: the historical air quality database comprises historical air quality data acquired by various air quality monitoring devices; the historical air quality data comprises two-dimensional geographic position information and time stamp information;
    2) establishing a three-dimensional space-time grid: the three-dimensional space-time grid takes a two-dimensional geographic position and time as an axis;
    3) establishing a gridding database: generating a unique data unit in each grid; the data cells are calculated from historical air quality data falling into the grid; or derived from neighboring grids of the grid;
    4) vectorizing analysis is carried out on the data of the gridding database to obtain the characteristic vectors of all or part of data units;
    5) comparing and matching the characteristics of the data units in the gridding database at the current period of time with the data units in the gridding database at the non-current period of time; obtaining one or more similar grid intervals with the highest matching degree;
    6) and predicting the value of the data unit in the future period by using the characteristic vector of the data unit in a period after the similar grid interval.
    2. A method for predicting atmospheric pollution comprises the following steps:
    1) establishing a historical air quality database: the historical air quality database comprises historical air quality data acquired by various air quality monitoring devices; the historical air quality data comprises two-dimensional geographic position information and time stamp information;
    2) establishing a three-dimensional space-time grid: the three-dimensional space-time grid takes a two-dimensional geographic position and time as an axis;
    3) establishing a gridding database: generating a unique data unit in each grid; the data cells are calculated from historical air quality data falling into the grid; or derived from neighboring grids of the grid;
    4) vectorizing analysis is carried out on the data of the gridding database to obtain the characteristic vectors of all or part of data units;
    5) comparing and matching the characteristic vector of the data unit in the gridding database at the current period of time with the characteristic vector of the data unit in the gridding database at the non-current period of time; obtaining one or more similar grid intervals with the highest matching degree;
    6) and predicting the value of the data unit in the future period by using the characteristic vector of the data unit in a period after the similar grid interval.
    3. The method of claim 1 or 2, wherein the size of each mesh in the three-dimensional spatiotemporal mesh is: two-dimensional geographical side length: 10-1000 m; duration: 1 minute-1 hour.
    4. The method of claim 1 or 2, wherein the partial data units do not include data units of a grid located at a boundary of a three-dimensional spatiotemporal grid.
    5. The method of claim 4, wherein the vectorization analysis is:
    respectively calculating the pollution contribution of each grid to the next period of the adjacent grid by a vector calculation mode to obtain:
    1) firstly, an analysis matrix is established
    Figure IMGF000022_0001
    2) Calculating a feature vector:
    Figure IMGF000022_0002
    wherein A ismnData representing a data unit with coordinates (m, n) at a certain time;
    the data of the data unit of (1) at the next time;
    Figure IMGF000022_0003
    contamination contribution of the peripheral mesh.
    6. The method of claim 4, wherein the data units are matched in a manner that: comparing the data units at the same grid position at the current moment and the historical moment to obtain a comparison coefficient
    Figure IMGF000022_0004
    AmnData being coordinates (m, n) of historical timeUnit, AvnA data unit that is the current time coordinate (m, n);
    in compliance with regulations
    Defining a similarity coefficient i, i =
    Data frames are dissimilar, 0 < 1 < K
    Figure IMGF000023_0001
    Similarly, 1> K
    K is similarity parameter, K = 0.8, 0.9
    7. The method of claim 4, wherein the feature vectors are matched in a manner that:
    Figure IMGF000023_0002
    wherein, Bm c nAcThe feature vector representing recent pollution drift, 1^ „ is the matching coefficient for the grid (m, n) at time 1.
    8. The method of claim 4, wherein the feature vectors are matched in a manner that:
    Figure IMGF000023_0003
    wherein ri is a matching coefficient of a grid (m, n) at a certain moment in a period of time T by applying an included angle cosine method, and q represents the matching times in the period of time T.
    9. The method of claim 4, wherein the feature vectors are matched in a manner that:
    Figure IMGF000023_0004
    wherein, rf is a matching coefficient rf of applying an included angle cosine method in the whole grid range within a period of time T, and q represents the matching times within the period of time T.
    10. Method according to one of claims 7 to 9, characterized in that the matching coefficients are modified in the following way: if = f X T1
    T1' is the matching coefficient after correction, f is the influence factor
    11. The method of claim 10, wherein the impact factor is determined by:
    Figure IMGF000024_0001
    12. the method of claim 4, wherein the prediction method is:
    and calculating and predicting future air quality data by using the current air quality data as a reference and utilizing the pollution drift vector of the matching grid at the subsequent moment and reversely applying a pollution drift vector calculation method to obtain the future air quality data.
CN201980006136.4A 2018-08-25 2019-02-15 Atmospheric pollution prediction method Active CN112513896B (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN201810965453 2018-08-25
CN2018109654536 2018-08-25
PCT/IB2019/051245 WO2020044127A1 (en) 2018-08-25 2019-02-15 Atmospheric pollution forecasting method

Publications (2)

Publication Number Publication Date
CN112513896A true CN112513896A (en) 2021-03-16
CN112513896B CN112513896B (en) 2023-05-23

Family

ID=69180628

Family Applications (5)

Application Number Title Priority Date Filing Date
CN201980006119.0A Active CN111788578B (en) 2018-07-25 2019-02-15 Environment monitoring station data credibility evaluation and calibration method
CN201980006136.4A Active CN112513896B (en) 2018-08-25 2019-02-15 Atmospheric pollution prediction method
CN201980089816.7A Active CN113330456B (en) 2018-08-25 2019-08-25 Method for predicting air pollution by utilizing historical air quality data characteristics
CN201980089855.7A Active CN113348471B (en) 2018-08-25 2019-08-25 Method for optimizing regional boundary in atmospheric pollution prediction
CN201980089866.5A Active CN113632101B (en) 2018-08-25 2019-08-25 Method for predicting atmospheric pollution through vectorization analysis

Family Applications Before (1)

Application Number Title Priority Date Filing Date
CN201980006119.0A Active CN111788578B (en) 2018-07-25 2019-02-15 Environment monitoring station data credibility evaluation and calibration method

Family Applications After (3)

Application Number Title Priority Date Filing Date
CN201980089816.7A Active CN113330456B (en) 2018-08-25 2019-08-25 Method for predicting air pollution by utilizing historical air quality data characteristics
CN201980089855.7A Active CN113348471B (en) 2018-08-25 2019-08-25 Method for optimizing regional boundary in atmospheric pollution prediction
CN201980089866.5A Active CN113632101B (en) 2018-08-25 2019-08-25 Method for predicting atmospheric pollution through vectorization analysis

Country Status (3)

Country Link
CN (5) CN111788578B (en)
GB (1) GB2591886A (en)
WO (2) WO2020021343A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113393058A (en) * 2021-07-14 2021-09-14 成都佳华物链云科技有限公司 Pollutant management and control method, prediction management and control method, real-time management and control method and device
CN113514611A (en) * 2021-06-28 2021-10-19 杭州谱育科技发展有限公司 Method for identifying pollutant transmission path
CN113536630A (en) * 2021-07-12 2021-10-22 西南科技大学 Method for acquiring pollutant inorganization emission factor

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112633779B (en) * 2021-02-25 2022-08-12 北京英视睿达科技股份有限公司 Method for evaluating reliability of environmental monitoring data
CN116187981B (en) * 2023-04-21 2023-07-25 广东工业大学 Microwave oven intelligent detection method based on historical maintenance data
CN117933466A (en) * 2024-01-23 2024-04-26 中科三清科技有限公司 Pollution prediction method and device, storage medium and electronic equipment

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104850913A (en) * 2015-05-28 2015-08-19 深圳先进技术研究院 Air quality PM2.5 predicating method and air quality PM2.5 predicating system
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
CN107991722A (en) * 2017-12-25 2018-05-04 北京墨迹风云科技股份有限公司 Method for building up, Forecasting Methodology and the prediction meanss of weather prediction model
CN108351866A (en) * 2015-11-12 2018-07-31 国际商业机器公司 Air pollution forecasting when ultrashort
US20180239057A1 (en) * 2017-02-22 2018-08-23 International Business Machines Corporation Forecasting air quality

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5582961A (en) * 1978-12-20 1980-06-23 Toshiba Corp Monitoring device for pollution of surface of the sea
US9053616B2 (en) * 2010-04-20 2015-06-09 Temptime Corporation Computing systems and methods for electronically indicating the acceptability of a product
CN102339445A (en) * 2010-07-23 2012-02-01 阿里巴巴集团控股有限公司 Method and system for evaluating credibility of network trade user
CN104008278B (en) * 2014-05-14 2017-02-15 昆明理工大学 PM2.5 concentration prediction method based on feature vectors and least square support vector machine
CN104200104A (en) * 2014-09-04 2014-12-10 浙江鸿程计算机系统有限公司 Fine granularity air pollutant concentration area estimation method based on spatial characteristics
CN104200103A (en) * 2014-09-04 2014-12-10 浙江鸿程计算机系统有限公司 Urban air quality grade predicting method based on multi-field characteristics
CN104280070B (en) * 2014-10-16 2017-02-01 北京中恒电国际信息技术有限公司 Big data cloud service concentrated environment monitoring platform
CN105589843B (en) * 2014-10-24 2019-02-26 科大讯飞股份有限公司 A kind of text word string matching process and system
WO2016129715A1 (en) * 2015-02-10 2016-08-18 주식회사 주빅스 Air quality prediction and management system for early detection of environmental disasters
CN104697568B (en) * 2015-02-13 2015-11-11 中国人民解放军海军工程大学 A kind of mixed type reliability test method of electronic product peculiar to vessel
CN104751242A (en) * 2015-03-27 2015-07-01 北京奇虎科技有限公司 Method and device for predicting air quality index
CN106325144A (en) * 2015-07-06 2017-01-11 湖州庆渔堂农业科技有限公司 Monitoring data calibration method and monitoring data calibration system of aquaculture monitoring system
CN105930653B (en) * 2016-04-19 2019-01-18 清华大学 A kind of pipeline exploding early warning method based on metering subregion flow monitoring data
CN106339775B (en) * 2016-08-23 2019-10-11 北京市环境保护监测中心 The air heavily contaminated case method of discrimination clustered based on weather typing and meteorological element
CN106644862B (en) * 2016-09-12 2023-08-29 山东诺方电子科技有限公司 A sensor(s) monitoring station based on sensor and monitoring method of monitoring station
CN106485353B (en) * 2016-09-30 2019-11-29 中国科学院遥感与数字地球研究所 Air pollutant concentration forecasting procedure and system
CN206756770U (en) * 2016-10-28 2017-12-15 神达电脑股份有限公司 Air quality monitoring system
WO2018214060A1 (en) * 2017-05-24 2018-11-29 北京质享科技有限公司 Small-scale air quality index prediction method and system for city
CN107609731A (en) * 2017-07-31 2018-01-19 贵州大学 A kind of Evaluation of Atmospheric Environmental Quality method
CN108229821A (en) * 2018-01-02 2018-06-29 中国神华能源股份有限公司 Appraisal procedure, device, storage medium and the system of mining area ecological environment

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104850913A (en) * 2015-05-28 2015-08-19 深圳先进技术研究院 Air quality PM2.5 predicating method and air quality PM2.5 predicating system
CN108351866A (en) * 2015-11-12 2018-07-31 国际商业机器公司 Air pollution forecasting when ultrashort
US20180239057A1 (en) * 2017-02-22 2018-08-23 International Business Machines Corporation Forecasting air quality
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
CN107991722A (en) * 2017-12-25 2018-05-04 北京墨迹风云科技股份有限公司 Method for building up, Forecasting Methodology and the prediction meanss of weather prediction model

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113514611A (en) * 2021-06-28 2021-10-19 杭州谱育科技发展有限公司 Method for identifying pollutant transmission path
CN113514611B (en) * 2021-06-28 2024-01-12 杭州谱育科技发展有限公司 Method for identifying pollutant transmission path
CN113536630A (en) * 2021-07-12 2021-10-22 西南科技大学 Method for acquiring pollutant inorganization emission factor
CN113536630B (en) * 2021-07-12 2023-09-29 西南科技大学 Method for obtaining unorganized emission factor of pollutant
CN113393058A (en) * 2021-07-14 2021-09-14 成都佳华物链云科技有限公司 Pollutant management and control method, prediction management and control method, real-time management and control method and device
CN113393058B (en) * 2021-07-14 2023-10-20 成都佳华物链云科技有限公司 Pollutant control method, prediction control method, real-time control method and device

Also Published As

Publication number Publication date
CN113348471A (en) 2021-09-03
CN113632101A (en) 2021-11-09
WO2020044127A1 (en) 2020-03-05
CN112513896B (en) 2023-05-23
CN113330456A (en) 2021-08-31
CN111788578A (en) 2020-10-16
GB202103044D0 (en) 2021-04-21
GB2591886A (en) 2021-08-11
CN113330456B (en) 2023-05-26
CN111788578B (en) 2023-10-20
WO2020021343A1 (en) 2020-01-30
CN113632101B (en) 2024-05-03
CN113348471B (en) 2023-07-18

Similar Documents

Publication Publication Date Title
CN112513896A (en) Method for predicting atmospheric pollution
WO2020043029A1 (en) Method for predicting air pollution by means of vectorization analysis
Chang et al. An LSTM-based aggregated model for air pollution forecasting
Wang et al. ClimateAP: An application for dynamic local downscaling of historical and future climate data in Asia Pacific
Arhami et al. Predicting hourly air pollutant levels using artificial neural networks coupled with uncertainty analysis by Monte Carlo simulations
CN109063908B (en) Urban AQI prediction and spatial fine-grained AQI grade estimation method based on deep multi-task learning
Marchant et al. Monitoring urban environmental pollution by bivariate control charts: New methodology and case study in Santiago, Chile
Dzupire et al. A Poisson‐Gamma Model for Zero Inflated Rainfall Data
CN114254802B (en) Prediction method for vegetation coverage space-time change under climate change drive
CN105488316A (en) Air quality prediction system and method
CN114997534B (en) Similar rainfall forecasting method and equipment based on visual features
CN113108918B (en) Method for inverting air temperature by using thermal infrared remote sensing data of polar-orbit meteorological satellite
CN113011455B (en) Air quality prediction SVM model construction method
CN115600643B (en) Method and system for rapidly predicting toxic gas
CN108764527B (en) Screening method for soil organic carbon library time-space dynamic prediction optimal environment variables
Zhu et al. Internal and external coupling of Gaussian mixture model and deep recurrent network for probabilistic drought forecasting
Bonas et al. Calibration of SpatioTemporal forecasts from citizen science urban air pollution data with sparse recurrent neural networks
CN114219345A (en) Secondary air quality prediction optimization method based on data mining
CN111445076B (en) Air pollution analysis method based on LSTM
Mahajan et al. Fidelity of precipitation extremes in high resolution global climate simulations
CN116822624A (en) Near-surface O3 estimation method based on depth forest model framework
CN113887058B (en) Chloride ion deposition rate prediction method considering influence of distance from coastline and wind speed
Annisa et al. Analysis and Projections of Rainfall using representative concentration pathways (RCPs) Scenarios in Sleman Yogyakarta
KR20050004316A (en) Prediction method of polluted air dispersion using multiple meteorological data
Lapkovsky et al. An approach to finding sources of pollution to maintain stable air quality

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