CN112861904A - Atmospheric pollution source monitoring and identifying method and system based on IMBI index - Google Patents
Atmospheric pollution source monitoring and identifying method and system based on IMBI index Download PDFInfo
- Publication number
- CN112861904A CN112861904A CN202011407478.8A CN202011407478A CN112861904A CN 112861904 A CN112861904 A CN 112861904A CN 202011407478 A CN202011407478 A CN 202011407478A CN 112861904 A CN112861904 A CN 112861904A
- Authority
- CN
- China
- Prior art keywords
- imbi
- concentration
- index
- monitoring
- remote sensing
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 23
- 239000005436 troposphere Substances 0.000 claims description 17
- 238000002485 combustion reaction Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 9
- 239000002028 Biomass Substances 0.000 claims description 8
- 239000003245 coal Substances 0.000 claims description 7
- 230000002265 prevention Effects 0.000 abstract description 2
- 238000012795 verification Methods 0.000 description 18
- 238000012360 testing method Methods 0.000 description 8
- 238000011010 flushing procedure Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000003066 decision tree Methods 0.000 description 5
- 239000003344 environmental pollutant Substances 0.000 description 5
- 238000007689 inspection Methods 0.000 description 5
- 231100000719 pollutant Toxicity 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005406 washing Methods 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011109 contamination Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 239000002912 waste gas Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an atmospheric pollution source monitoring and identifying method and system based on IMBI index, wherein NO of the near ground of a monitoring area is obtained by setting an analysis model in the method and the system2And the concentration of CO, and further taking the ratio of the two as an IMBI index, judging the type of a main pollution source in a monitoring area according to the numerical range of the IMBI index, and giving a treatment scheme according to the specific type in a targeted manner, so that the atmosphere pollution prevention and control level is improved, and the content of PM2.5 in the atmosphere is reduced at low cost and high efficiency.
Description
Technical Field
The invention relates to the technical field of environmental monitoring, in particular to an atmospheric pollution source monitoring and identifying method and system based on IMBI indexes.
Background
Although the concentration of PM2.5 in our country is continuously reduced, the annual average concentration of PM2.5 in some cities is not up to the standard, the pollution treatment task is difficult, and meanwhile, the ozone pollution is increasingly serious in summer, and PM2.5 is replaced in some cities to become a main pollution factor affecting good days. NO2And CO as important precursors for PM2.5 and O3 by the reaction on NO2And CO high value area monitoring, identifying atmospheric pollution source, for PM2.5 and O3The cooperative control of (A) has important significance.
NO2Mainly generated by combustion of fossil fuel in traffic and industrial processes, the combustion temperature requirement is higher, the more full the fuel is combusted, NO in the discharged waste gas2The higher the concentration. CO is also mainly emitted from man-made sources, and carbon-containing fuelCarbon monoxide is produced by incomplete combustion, and the worse the oxygen supply condition is, the higher the CO content in the discharged waste gas is. The artificial emission sources of the two pollutant concentrations are relatively consistent and mainly come from industrial sources, mobile sources, biomass combustion and the like, meanwhile, the artificially emitted gaseous pollutants mainly exist in the middle-low layer of the troposphere, and the problem that the atmospheric pollution sources which emit the two gaseous pollutants exist in two aspects is directly monitored and identified by satellite remote sensing: firstly, troposphere NO is obtained by satellite remote sensing monitoring and inversion2And the concentration of the CO column, which can not directly reflect the human source emission condition; secondly, although the two gaseous pollutants have consistent emission sources, NO can not be distinguished by singly using one of the pollutants2And from which pollution source the high CO value zone is primarily derived. How to obtain near-surface NO2And CO concentration, and accurately distinguishing and positioning industrial sources, mobile sources and combustion sources, and is an important problem for scientifically and accurately treating pollution in the current atmospheric pollution treatment.
For the reasons, the inventor conducts deep research on the existing atmospheric pollution source monitoring method and designs an atmospheric pollution source monitoring and identifying method and system based on IMBI index, which can solve the problems.
Disclosure of Invention
In order to overcome the problems, the inventor of the present invention has conducted intensive research to design a method and a system for monitoring and identifying an atmospheric pollution source based on an IMBI index, wherein an analysis model is set in the method and the system to obtain NO near the ground of a monitored area2And the concentration of CO, and further taking the ratio of the two as an IMBI index, judging the type of a main pollution source in a monitoring area according to the numerical range of the IMBI index, and giving a treatment scheme according to the specific type in a targeted manner, so that the atmosphere pollution prevention and control level is improved, and the content of PM2.5 in the atmosphere is reduced at low cost and high efficiency, thereby completing the invention.
Specifically, the invention aims to provide an atmospheric pollution source monitoring and identifying method based on IMBI index, which comprises the following steps
Wherein, in step 1, the sample comprises:
troposphere NO obtained by satellite remote sensing information inversion2The column concentration and the CO column concentration,
near-surface NO obtained by surface monitoring station2The concentration of CO, and
meteorological conditions; the meteorological conditions include air temperature, humidity, and wind speed.
Wherein, in step 3, the IMBI index is based on near-surface CO concentration and near-surface NO2The ratio of the concentrations is obtained.
Wherein, in step 3, the judging the pollution condition of the monitoring area comprises:
IMBI<200 and NO2The regular remote sensing unit with the concentration value of the first 20 percent is an urban mobile source or an urban industrial source,
the regular remote sensing unit with IMBI more than or equal to 200 and less than 400 and CO concentration value in the first 20 percent is an industrial source,
and the regular remote sensing unit with IMBI more than or equal to 400 and CO concentration value in the first 20% is a residential fire coal or biomass combustion source.
In step 3, if the regular remote sensing unit is the heart city region, the IMBI is more than or equal to 400, and the CO value is in the top 20%, the regular remote sensing unit is a pollution source of the motor vehicle.
In step 3, after the pollution condition of the monitored area is judged to be finished, the high-pollution area is highlighted in a frame selection mode.
The invention also provides an atmospheric pollution source monitoring and identifying system based on the IMBI index, which comprises:
analytical model for determining NO in troposphere from monitored region2Column concentration, CO column concentration and meteorological conditions of a monitored area, and obtaining NO near the ground of the monitored area2And the concentration of CO;
a judgment and screening module for judging NO near the ground according to the monitoring area2And obtaining the IMBI index of the monitored area according to the concentration of the CO, and judging the pollution condition of the monitored area according to the IMBI index.
Wherein the analysis model is obtained by sample training, and the sample comprises:
troposphere NO obtained by satellite remote sensing information inversion2The column concentration and the CO column concentration,
near-surface NO obtained by surface monitoring station2The concentration of CO, and
meteorological conditions; the meteorological conditions include air temperature, humidity, and wind speed.
Wherein, in the judgment and screening module, the near-surface CO concentration and the near-surface NO are determined2The ratio of concentrations gives the IMBI index.
Wherein, in the judgment and screening module,
IMBI<200 and NO2The regular remote sensing unit with the concentration value of the first 20 percent is an urban mobile source or an urban industrial source,
the regular remote sensing unit with IMBI more than or equal to 200 and less than 400 and CO concentration value in the first 20 percent is an industrial source,
and the regular remote sensing unit with IMBI more than or equal to 400 and CO concentration value in the first 20% is a residential fire coal or biomass combustion source.
The invention has the advantages that:
(1) according to the atmospheric pollution source monitoring and identifying method and system based on IMBI index provided by the invention, NO on the near ground of the monitored area can be quickly and accurately obtained through the analysis module2And CO concentration, thereby enabling the system and method to operate without NO loading2Monitoring the pollution condition in the area of the CO detection equipment, and improving the overall adaptability;
(2) according to the atmospheric pollution source monitoring and identifying method and system based on the IMBI index, provided by the invention, the IMBI index can be obtained, the main pollution source type of the monitoring area is judged according to the numerical range of the IMBI index, and a reliable data information basis is provided for accurately treating pollution.
Drawings
FIG. 1 is a logic diagram of an overall atmospheric pollution source monitoring and identifying method based on IMBI indexes according to a preferred embodiment of the invention;
FIG. 2 shows the NO obtained in the example on the near ground of Jingjin Ji Heyu area2A concentration profile;
FIG. 3 shows the distribution diagram of the CO concentration on the near ground of Jingjin Ji Heyu area obtained in the example;
FIG. 4 shows the distribution diagram of the near-surface IMBI of Kyoto Jiu Yu area obtained in the example;
FIG. 5 shows the highlighted neighborhood of the Hubei Tangshan national Tegang coke-oven plant of the example and its enlarged view;
FIG. 6 shows the area around Bingzhen on Tianjin Cizhou area highlighted in the example and its enlarged view;
FIG. 7 is a view showing an area around Tugontun town, Texas, Shandong, and its enlarged view, highlighted in the example;
FIG. 8 is a view showing an area around a village of a four street in the eight-mile camp city, Anyang, Henan province, highlighted in the example and an enlarged view thereof;
fig. 9 shows an area around the wuying village of toming town of toming, lotus, east province of the river mountain highlighted in the example and an enlarged view thereof.
Detailed Description
The invention is explained in more detail below with reference to the figures and examples. The features and advantages of the present invention will become more apparent from the description.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
According to the atmospheric pollution source monitoring and identifying method based on the IMBI index, as shown in FIG. 1, the method comprises the following steps:
In a preferred embodiment, in step 1, the sample comprises:
troposphere NO obtained by satellite remote sensing information inversion2The column concentration and the CO column concentration,
near-surface NO obtained by surface monitoring station2The concentration of CO, and
meteorological conditions; the meteorological conditions include air temperature, humidity, and wind speed.
Through a large number of sample flushing training, the analysis model receives troposphere NO2The column concentration, the CO column concentration and the corresponding meteorological conditions can obtain the corresponding NO near the ground2And CO concentration.
The training sample can select NO corresponding to any plurality of areas in the global scope2Column concentration, CO column concentration, and meteorological conditions.
In a preferred embodiment, the step 1 comprises the following sub-steps:
and a substep 4 of obtaining an analytical model based on the data available in substep 3.
In particular, in sub-stepsIn step 1, the near-surface NO of the area corresponding to a regular remote sensing unit is called2And the concentration of CO, the meteorological conditions of the area, namely the temperature, the humidity and the wind speed of the near ground of the area corresponding to the regular remote sensing unit are obtained, and then the troposphere NO of the area corresponding to the regular remote sensing unit is obtained through inversion2And the column concentration and the CO column concentration are collected into a basic data, and the basic data is the basic data of sample training. In the actual working process, at least more than 3000 pieces of basic data are required to be called each time the basic data are called.
The substep 2 comprises the following substeps;
a sub-substep 1, dividing all basic data into two groups randomly according to a preset proportion, namely a learning group and a checking group; preferably, the ratio may be 15-25: 1, more preferably, the ratio of the number of data in the learning group to the number of data in the test group is 19: 1;
a sub-step 2, flushing the model by using the data in the learning group, verifying the model one by using each data in the inspection group, and respectively recording the verification result of each data in the inspection group, wherein preferably, the verification result comprises a verification pass and a verification fail; wherein, the verification pass refers to the troposphere NO of the basic data in the test group2The column concentration, the CO column concentration and the meteorological conditions are brought into the model to obtain near-surface NO2Concentration of CO and near-surface NO in the basic data2The concentration of CO is close, i.e. the error is below 3%, preferably the concentration is close when the difference between the obtained value and the true value is divided by the true value and the result is less than or equal to 3%, further, NO is solved independently of each other2And errors of CO, and the verification is judged to be successful when the errors of the two are below 3%.
Verification of failure means that the tropospheric NO of the underlying data in the test set will be verified2The column concentration, the CO column concentration and the meteorological conditions are brought into the model to obtain near-surface NO2Concentration of CO and near-surface NO in the basic data2The concentration of CO is inconsistent, i.e. the error is more than 3%.
A sub-step 3, repeating the sub-step 1 and the sub-step 2 for a plurality of times, wherein basic data once distributed into the inspection group is not distributed into the inspection group any more, and each basic data is ensured to verify the model flushed by the data in the learned group in the inspection group until the verification results corresponding to all the basic data are obtained;
a sub-step 4 of calculating the total passing rate of all basic data verification results, wherein the total passing rate is the ratio of the verification passing quantity to the verification passing quantity of all basic data; when the total passing rate is not more than 80%, the basic data are considered to be not in accordance with the basic requirements, all basic data are abandoned, substep 1 is repeated, and new basic data are obtained again; and when the result in the sub-substep 4 is that the total passing rate is greater than 80%, the basic data are considered to meet the use requirements, namely the basic data meeting the requirements, and the next step of processing can be carried out.
In a preferred embodiment, the obtaining of the available data in substep 3 comprises the substeps of:
a sub-step a, repeating sub-steps 1-3 in sub-step 2 for a plurality of times, and obtaining a checking group consisting of different basic data when repeating sub-step 1 each time, namely all checking groups are different; preferably, the sub-substeps 1 to 3 are repeated for 20 to 30 times, so that each basic data corresponds to a plurality of verification results, and then the average passing rate corresponding to each basic data is respectively calculated; the average passing rate corresponding to the basic data is the ratio of the number of passing verification in the verification results corresponding to the basic data to the total number of the verification results corresponding to the basic data.
A sub-step b, finding and hiding 5 pieces of basic data with the lowest average passing rate, and hiding 5 pieces of basic data randomly when the average passing rates of more than 6 pieces of basic data are consistent and the lowest, namely randomly extracting when data values are parallel, wherein the hidden data do not participate in any calculation processing before being recovered; finding and utilizing the residual basic data to execute sub-steps 1-4 again, observing whether the total passing rate is increased compared with that before hiding the data, if the total passing rate is increased, deleting the hidden basic data, and executing sub-step c; if the total passing rate is not improved, recovering the hidden basic data, continuously selecting and hiding the basic data with the lowest average passing rate, wherein the data which is once hidden and then recovered cannot be selected again, and adding a special mark after the basic data is recovered; repeating the processes until the total passing rate is increased;
a sub-step c, repeating the sub-step a and the sub-step b based on the residual basic data after the total passing rate is increased, and eliminating the special mark on the data in the repeating process; after the total passing rate is found to be improved, continuously repeating the sub-step a and the sub-step b on the basis of the current residual basic data until the total passing rate reaches more than 90%, preferably more than 95%; or until the deleted basic data reaches 20% of the total basic data, and the remaining basic data is the available data.
Preferably, the models in the substep 2 include most models with supervised learning, and the washing process of the models includes comprehensive judgment of a plurality of supervised models, and the specific washing process includes, but is not limited to, washing methods using linear regression, support vector machine, gradient descent method, naive bayes classification, decision tree classification, AdaBoost, XGBoost, multilayer neural network, and the like. Preferably, the average value of 2 results which are closer to each other in the results of the neural network with the 3-4 layers, the C4.5 decision tree and the XGboost 3 models is used as an output value of each flushing, namely, the neural network with the 3-4 layers, the C4.5 decision tree and the XGboost are combined into the most preferable model, namely the model with high ecological utility.
In sub-step 4, in the process of obtaining the analytical model, the tropospheric NO in each available data is determined2Column concentration, CO column concentration, meteorological conditions and near-surface NO2Splicing the concentration of CO into a data segment which is used as a learning material, and obtaining an analysis model through machine learning;
in a preferred embodiment, in step 4, a 3-4-layer structured neural network, C4.5 decision tree is built by using the integrated neural activity index and label data in the process of obtaining an analysis model learning by using available dataAnd the XGboost model is combined with the XGboost model to serve as an analysis model, and the output of the analysis model is the average value of the two closest output values in the outputs of the three models. For example, for a set of data, three models each give an output of 6, 15, and 7, with output 7 and output 6 being close to each other, the final analysis model has an output of 6, i.e., an average of 7 and 6, and rounded down, where NO2The concentration and the CO concentration were calculated separately.
The near-ground surface as referred to in this application means a space region having a height of about 50 to 100 m.
The ground monitoring station is an observation site which is uniformly coordinated and controlled by the world meteorological organization of the United nations and comprises related equipment for measuring air temperature, humidity and wind speed.
In a preferred embodiment, in step 3, the IMBI index is based on near-surface CO concentration and near-surface NO2The ratio of the concentrations is obtained.
Namely:
in a preferred embodiment, in step 3, determining the contamination status of the monitored area comprises:
IMBI<200 and NO2The regular remote sensing unit with the concentration value of the first 20 percent is an urban mobile source or an urban industrial source. Specifically, the monitoring area is divided into a plurality of regular remote sensing units, the IMBI value of each regular remote sensing unit is judged respectively, and the NO corresponding to all the regular remote sensing units is judged simultaneously2Concentration values and sorting by size to select NO2Concentration values ranked 20% top and IMBI<200, the area range referred by the selected rule remote sensing unit is the urban mobile source or the urban industrial source, namely the high pollution area. The regular remote sensing unit described in the application is a rectangular frame selection unit which represents a specific ground area in a satellite remote sensing image, and specific grid sizes can be set according to practical conditions such as resolution and the like, such as 3.5km × 3.5km, 3.5km × 7km, 7km × 7km and the like.
The regular remote sensing unit with IMBI more than or equal to 200 and less than 400 and CO concentration value in the first 20 percent is an industrial source,
and the regular remote sensing unit with IMBI more than or equal to 400 and CO concentration value in the first 20% is a residential fire coal or biomass combustion source.
In a preferred embodiment, in step 3, if the regular remote sensing unit is the heart city area, the IMBI is more than or equal to 400, and the CO value is in the top 20%, the regular remote sensing unit is the pollution source of the motor vehicle.
In the present application, it is preferred that when the PM2.5 concentration in the monitored area is greater than 75 μ g/m3Or CO concentration greater than 200 x 1016molec./cm2The above-mentioned pollution condition is judged only when the PM2.5 concentration in the monitored area is 75 μ g/m3Below and CO concentration at 200 x 1016molec./cm2In the following, no contamination source was present.
Further preferably, in step 3, after the pollution condition of the monitored area is judged to be completed, the high-pollution area is highlighted in a frame selection mode, that is, the high-pollution area is selected by a wire frame, and the high-pollution area is locally amplified, so that specific coordinates and topographic information of the high-pollution area can be accurately obtained.
Preferably, the general area of the monitoring area is the administrative coverage of a grade city.
The invention also provides an atmospheric pollution source monitoring and identifying system based on the IMBI index, which comprises an analysis model and a judgment and screening module.
Analytical model for tropospheric NO based on monitored area2Column concentration, CO column concentration and meteorological conditions of a monitored area, and obtaining NO near the ground of the monitored area2And the concentration of CO;
the judging and screening module is used for judging NO on the near ground of the monitoring area2And obtaining the IMBI index of the monitored area according to the concentration of the CO, and judging the pollution condition of the monitored area according to the IMBI index.
Preferably, the analysis model is obtained by training a sample, and the sample comprises:
remote sensing via satelliteTroposphere NO obtained by information inversion2The column concentration and the CO column concentration,
near-surface NO obtained by surface monitoring station2The concentration of CO, and
meteorological conditions; the meteorological conditions include air temperature, humidity, and wind speed.
Preferably, in the judgment screening module, the near-surface CO concentration and the near-surface NO are measured2The ratio of concentrations gives the IMBI index.
Preferably, in the judgment screening module,
IMBI<200 and NO2The regular remote sensing unit with the concentration value of the first 20 percent is an urban mobile source or an urban industrial source;
the regular remote sensing unit with IMBI more than or equal to 200 and less than 400 and CO concentration value in the first 20 percent is an industrial source,
and the regular remote sensing unit with IMBI more than or equal to 400 and CO concentration value in the first 20% is a residential fire coal or biomass combustion source.
Further, after the pollution condition of the monitored area is judged, the high-pollution area is highlighted in a frame selection mode.
Examples
Method for calling near-ground NO from state control monitoring station database2And CO concentration and meteorological conditions, extracting thermal infrared hyperspectral data from the AIRS database, and performing inversion according to the thermal infrared hyperspectral data to obtain troposphere NO2Column concentration and CO column concentration, and the near-surface NO of the region corresponding to each regular remote sensing unit2Concentration, near-surface CO concentration, near-surface meteorological conditions, tropospheric NO2The column concentration and the CO column concentration are integrated into one basic data, and 3000 basic data are called.
Randomly dividing all 3000 pieces of basic data into 20 parts, wherein one part is used as a test group, the other parts are used as learning groups, flushing the model through the learning groups, and verifying the model by using the data in the test groups to obtain the verification result of each test group data; and repeating the steps by using the data in other parts as a check group, repeating the steps for 150 times in total, and ensuring that each basic data is distributed to the check group once, namely each basic data obtains a corresponding verification result, the total passing rate is 88 percent and is higher than 80 percent, and the next step of processing can be carried out.
And eliminating abnormal data in the basic data to obtain usable data, specifically,
calculating the average passing rate, randomly dividing all 3000 pieces of basic data into 20 parts, taking one part as a test group and the other parts as a learning group, flushing the model through the learning group, and verifying the model by using the data in the test group to obtain the verification result of each piece of data; then, the checking group and the learning group are redistributed, the process is repeated for at least 1500 times, each basic data is guaranteed to be distributed into the checking group for at least 10 times, namely each basic data obtains 10 corresponding verification results, and further the average passing rate of each basic data is obtained;
finding and hiding 5 pieces of basic data with the lowest average passing rate, utilizing the rest 2995 pieces of basic data to execute the process of obtaining the total passing rate again, observing whether the total passing rate is increased compared with that before hiding the data, and deleting the hidden basic data if the total passing rate is increased; if the total passing rate is not improved, recovering the hidden basic data, making special marks on the recovered basic data, not selecting/hiding the basic data again, selecting 5 basic data with the lowest average passing rate from the rest basic data, and repeating the process of obtaining the total passing rate until the total passing rate is improved;
after the hit rate is increased, the hidden data is deleted, the process of obtaining the average passing rate is continuously executed based on the rest basic data, in the process, the data which is once marked by the special mark cancels the special mark, and can be selected/hidden before being marked again. Calculating the average passing rate corresponding to each basic data, searching and hiding 5 basic data with the lowest average passing rate, calculating the total passing rate on the basis of hiding the data with the lowest average passing rate, and continuously repeating the removing process until the total passing rate reaches 95%.
The remaining data at this time is referred to as usable data.
The analytical model is trained on the available data and, in particular,
and (3) flushing a neural network with a 3-4 layer structure, a C4.5 decision tree and an XGboost calculation module by using available data to obtain an analysis model combined by the three models, wherein the output value of the analysis model is the average value of 2 closer values in 3 model outputs given by the three models, so that the analysis model is obtained.
After the analysis model is obtained, the satellite remote sensing information of 2 months in 2019 of Jingjin Ji Luyu area is called, and NO in the troposphere is obtained through inversion2The column concentration and the CO column concentration are obtained, and the temperature, humidity and wind speed information of the area in 2019 and 2 months are taken and input into the analysis model together, so that NO on the ground in the area near 2019 and 2 months of Jingjin Jilu Yu is obtained2And CO concentration, as shown in fig. 2 and 3, and further obtain the IMBI value of kyujilu yu region, as shown in fig. 4.
According to the judgment conditions described below, the judgment conditions,
IMBI<200 and NO2The regular remote sensing unit with the concentration value of the first 20 percent is an urban mobile source or an urban industrial source,
the regular remote sensing unit with IMBI more than or equal to 200 and less than 400 and CO concentration value in the first 20 percent is an industrial source,
the rule remote sensing unit with IMBI more than or equal to 400 and CO concentration value in the first 20% is a residential fire coal or biomass combustion source;
the highly contaminated area in kyford jilu yun area was selected in block as shown in fig. 5, 6, 7, 8 and 9.
Wherein FIG. 5 shows the highlighting of the area near Hebei Tangshan national Teddy coke-oven plant as a highly contaminated area by means of a frame selection, the near-surface NO in the regular remote sensing unit2Concentration value of 8.59 x 1015molec./cm2Near-surface CO concentration value of 250 x 1016molec./cm2The IMBI value is 291, and the pollution source type corresponding to the rule remote sensing unit is an industrial source;
FIG. 6 shows a box selection mode for highlighting the area near the Bingzhen area of Tianjin City Jizhou as a high pollution area, and the near-surface NO in the regular remote sensing unit2Concentration value of 5.05 x 1015molec./cm2Near the ground CO concentration value of 215 × 1016molec./cm2The IMBI value is 426, and the pollution source type corresponding to the rule remote sensing unit is a resident coal-burning source;
FIG. 7 shows a case where the region near Lu rights Tun Town, Tex, Shandong is highlighted as a highly polluted region by frame selection, and the near-surface NO in the regular remote sensing unit2Concentration value of 5.53 x 1015molec./cm2Near-surface CO concentration value of 223 x 1016molec./cm2The IMBI value is 403, and the pollution source type corresponding to the rule remote sensing unit is a resident coal-fired source;
FIG. 8 shows a case where the area around the four villages in the eight-Li Yingzhen city, Anyang, Henan province is highlighted as a highly polluted area by frame selection, and the NO on the near surface in the regular remote sensing unit2Concentration value of 4.01 x 1015molec./cm2Near-surface CO concentration value of (202 × 10)16molec./cm2The IMBI value is 504, and the pollution source type corresponding to the rule remote sensing unit is a resident coal-burning source;
FIG. 9 shows a case where the area around the Wuying village of the Toming town of Neze, Shandong province, which is highlighted by frame selection as a highly polluted area by the near-surface NO in the regular remote sensing unit2Concentration value of 4.22 x 1015molec./cm2Near-surface CO concentration value of (212 × 10)16molec./cm2The IMBI value is 502, and the pollution source type corresponding to the rule remote sensing unit is a residential coal-fired source.
The present invention has been described above in connection with preferred embodiments, but these embodiments are merely exemplary and merely illustrative. On the basis of the above, the invention can be subjected to various substitutions and modifications, and the substitutions and the modifications are all within the protection scope of the invention.
Claims (10)
1. An atmospheric pollution source monitoring and identifying method based on IMBI index is characterized by comprising the following steps
Step 1, training an analysis model through a sample,
step 2, calling satellite remote sensing information of the monitored area, and obtaining NO in the troposphere through inversion2Column concentration and CO column concentration, and then takingThe meteorological conditions of the monitored area are input into the analysis model, and NO of the near ground of the monitored area is obtained2And the concentration of the CO,
step 3, according to NO near the ground of the monitored area2And obtaining the IMBI index of the monitoring area according to the concentration information of the CO, and judging the pollution condition of the monitoring area according to the IMBI index.
2. The method for monitoring and identifying atmospheric pollution sources based on IMBI index as recited in claim 1,
in step 1, the sample comprises:
troposphere NO obtained by satellite remote sensing information inversion2The column concentration and the CO column concentration,
near-surface NO obtained by surface monitoring station2The concentration of CO, and
meteorological conditions; the meteorological conditions include air temperature, humidity, and wind speed.
3. The method for monitoring and identifying atmospheric pollution sources based on IMBI index as recited in claim 1,
in step 3, the IMBI index is determined by near surface CO concentration and near surface NO2The ratio of the concentrations is obtained.
4. The method for monitoring and identifying atmospheric pollution sources based on IMBI index as recited in claim 1,
in step 3, the determining the pollution condition of the monitored area includes:
IMBI<200 and NO2The regular remote sensing unit with the concentration value of the first 20 percent is an urban mobile source or an urban industrial source;
the regular remote sensing unit with IMBI more than or equal to 200 and less than 400 and CO concentration value in the first 20 percent is an industrial source,
and the regular remote sensing unit with IMBI more than or equal to 400 and CO concentration value in the first 20% is a residential fire coal or biomass combustion source.
5. The method for monitoring and identifying atmospheric pollution sources based on IMBI index as recited in claim 4,
in step 3, if the regular remote sensing unit is the heart city region, the IMBI is more than or equal to 400, and the CO value is in the first 20%, the regular remote sensing unit is a pollution source of the motor vehicle.
6. The method for monitoring and identifying atmospheric pollution sources based on IMBI index as recited in claim 1,
in step 3, after the pollution condition of the monitored area is judged to be finished, the high-pollution area is highlighted in a frame selection mode.
7. Atmospheric pollution source monitoring and identifying system based on IMBI index is characterized in that the system comprises:
analytical model for determining NO in troposphere from monitored region2Column concentration, CO column concentration and meteorological conditions of a monitored area, and obtaining NO near the ground of the monitored area2And the concentration of CO;
a judgment and screening module for judging NO near the ground according to the monitoring area2And obtaining the IMBI index of the monitored area according to the concentration of the CO, and judging the pollution condition of the monitored area according to the IMBI index.
8. The IMBI index based atmospheric pollution source monitoring and identification system as claimed in claim 7,
the analytical model is obtained by sample training,
the sample includes:
troposphere NO obtained by satellite remote sensing information inversion2The column concentration and the CO column concentration,
near-surface NO obtained by surface monitoring station2The concentration of CO, and
meteorological conditions; the meteorological conditions include air temperature, humidity, and wind speed.
9. The IMBI index based atmospheric pollution source monitoring and identification system as claimed in claim 7,
in the judgment and screening module, the near-surface CO concentration and the near-surface NO are determined2The ratio of concentrations gives the IMBI index.
10. The IMBI index based atmospheric pollution source monitoring and identification system as claimed in claim 7,
in the judgment screening module, the judgment screening module is used for judging whether the judgment is correct,
IMBI<200 and NO2The regular remote sensing unit with the concentration value of the first 20 percent is an urban mobile source or an urban industrial source;
the regular remote sensing unit with IMBI more than or equal to 200 and less than 400 and CO concentration value in the first 20 percent is an industrial source,
and the regular remote sensing unit with IMBI more than or equal to 400 and CO concentration value in the first 20% is a residential fire coal or biomass combustion source.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011407478.8A CN112861904B (en) | 2020-12-04 | 2020-12-04 | Atmospheric pollution source monitoring and identifying method and system based on IMBI index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011407478.8A CN112861904B (en) | 2020-12-04 | 2020-12-04 | Atmospheric pollution source monitoring and identifying method and system based on IMBI index |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112861904A true CN112861904A (en) | 2021-05-28 |
| CN112861904B CN112861904B (en) | 2021-11-05 |
Family
ID=75996952
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011407478.8A Active CN112861904B (en) | 2020-12-04 | 2020-12-04 | Atmospheric pollution source monitoring and identifying method and system based on IMBI index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112861904B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114218976A (en) * | 2021-09-27 | 2022-03-22 | 中国环境科学研究院 | Method and system for tracing and positioning fine emission source in ozone precursor high-value area |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5128268A (en) * | 1989-06-20 | 1992-07-07 | President And Fellows Of Harvard College | Halogen/charge-transfer complex gas monitor |
| CN109357716A (en) * | 2018-11-26 | 2019-02-19 | 河南大瑞物联网科技有限公司 | A kind of heavily contaminated local pollution control data real-time collection method |
| CN109543990A (en) * | 2018-11-19 | 2019-03-29 | 北京英视睿达科技有限公司 | The method and device of atmosphere pollution hot spot grid is determined based on pollution sources |
| CN110308104A (en) * | 2019-06-25 | 2019-10-08 | 生态环境部卫星环境应用中心 | A kind of atmosphere pollution NO2Concentration monitoring method and system |
| CN110567510A (en) * | 2019-07-23 | 2019-12-13 | 北京英视睿达科技有限公司 | Atmospheric pollution monitoring method, system, computer equipment and storage medium |
| CN110942049A (en) * | 2019-12-17 | 2020-03-31 | 生态环境部卫星环境应用中心 | Ozone pollution source identification method and system based on satellite remote sensing |
| CN111414571A (en) * | 2020-04-01 | 2020-07-14 | 浙江工业大学 | Atmospheric pollutant monitoring method |
-
2020
- 2020-12-04 CN CN202011407478.8A patent/CN112861904B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5128268A (en) * | 1989-06-20 | 1992-07-07 | President And Fellows Of Harvard College | Halogen/charge-transfer complex gas monitor |
| CN109543990A (en) * | 2018-11-19 | 2019-03-29 | 北京英视睿达科技有限公司 | The method and device of atmosphere pollution hot spot grid is determined based on pollution sources |
| CN109357716A (en) * | 2018-11-26 | 2019-02-19 | 河南大瑞物联网科技有限公司 | A kind of heavily contaminated local pollution control data real-time collection method |
| CN110308104A (en) * | 2019-06-25 | 2019-10-08 | 生态环境部卫星环境应用中心 | A kind of atmosphere pollution NO2Concentration monitoring method and system |
| CN110567510A (en) * | 2019-07-23 | 2019-12-13 | 北京英视睿达科技有限公司 | Atmospheric pollution monitoring method, system, computer equipment and storage medium |
| CN110942049A (en) * | 2019-12-17 | 2020-03-31 | 生态环境部卫星环境应用中心 | Ozone pollution source identification method and system based on satellite remote sensing |
| CN111414571A (en) * | 2020-04-01 | 2020-07-14 | 浙江工业大学 | Atmospheric pollutant monitoring method |
Non-Patent Citations (4)
| Title |
|---|
| CHUNYAN Z.等: "Spatio-temporal change and influencing factors of tropospheric NO2 column density of Beijing-Tianjin-Hebei Region in the decade based OMI product", 《2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS)》 * |
| SRIJANA L.等: "Quantifying burning efficiency in Megacities using NO2/CO ratio from the Tropospheric Monitoring Instrument (TROPOMI)", 《EGU GENERAL ASSEMBLY 2020》 * |
| 刘森林: "生态环境保护中污染源自动监测技术的运用", 《云南化工》 * |
| 曹欢 等: "基于PIE的大气污染遥感监测系统的设计与实现", 《地理空间信息》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114218976A (en) * | 2021-09-27 | 2022-03-22 | 中国环境科学研究院 | Method and system for tracing and positioning fine emission source in ozone precursor high-value area |
| CN114218976B (en) * | 2021-09-27 | 2024-03-08 | 中国环境科学研究院 | Method and system for tracing and positioning refined emission source in high-value area of ozone precursor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112861904B (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Borck et al. | Population density and urban air quality | |
| CN110242865B (en) | Gas leakage detection and judgment method and system easy for continuous optimization | |
| CN116011317B (en) | Small-scale near-real-time atmospheric pollution tracing method based on multi-method fusion | |
| Shao et al. | Uncertainty analysis of terrestrial net primary productivity and net biome productivity in China during 1901–2005 | |
| Isiyaka et al. | Air quality pattern assessment in Malaysia using multivariate techniques | |
| CN114662344B (en) | Atmospheric pollution source tracing prediction method and system based on continuous online observation data | |
| CN112669976B (en) | Crowd health assessment method and system based on ecological environment change | |
| CN112861904B (en) | Atmospheric pollution source monitoring and identifying method and system based on IMBI index | |
| CN107480781A (en) | The nuclear accident Source Term Inversion method of neutral net adaptive Kalman filter | |
| CN115186437B (en) | Carbon isotope combined assimilation model and construction method of assimilation system for discriminating artificial carbon emission and natural carbon flux areas | |
| RU2397514C1 (en) | Method of constructing network of posts for monitoring air pollution and determining characteristics of pollution sources | |
| CN109753720A (en) | Air quality monitoring data exception checks method, system, equipment and medium | |
| Kapadia et al. | Prediction of tropospheric ozone using artificial neural network (ANN) and feature selection techniques | |
| Hua | Applied chemometric approach in identification sources of air quality pattern in Selangor, Malaysia | |
| AhmadIsiyaka et al. | Spatial assessment of air pollution index using environ metric modeling techniques | |
| Krishnaveni et al. | Aerosol classification using fuzzy clustering over a tropical rural site | |
| Lee et al. | Past and recent changes in the pollution characteristics of PM10 and SO2 in the largest industrial city in South Korea | |
| Azid et al. | Spatial air quality modelling using chemometrics techniques: A case study in Peninsular Malaysia | |
| CN117312784A (en) | Pollution source tracing method based on receptor model and big data combination | |
| CN115239027B (en) | Method and device for forecasting air quality check set | |
| CN114896952B (en) | Method and device for compiling emission list of atmospheric pollution sources | |
| CN112986497B (en) | Pollution gas tracing method based on gas sensor array fingerprint identification | |
| Campanile et al. | Applying machine learning to weather and pollution data analysis for a better management of local areas: the case of Napoli, Italy | |
| CN113378380A (en) | Numerical simulation-based method for tracing source of pollutants in underground water | |
| CN117542434B (en) | Air pollutant concentration analysis method based on data analysis |
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 |