CN117390971B - Method and system for estimating NO2 concentration based on heating season - Google Patents
Method and system for estimating NO2 concentration based on heating season Download PDFInfo
- Publication number
- CN117390971B CN117390971B CN202311675528.4A CN202311675528A CN117390971B CN 117390971 B CN117390971 B CN 117390971B CN 202311675528 A CN202311675528 A CN 202311675528A CN 117390971 B CN117390971 B CN 117390971B
- Authority
- CN
- China
- Prior art keywords
- data
- heating
- hour
- region
- concentration
- 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.)
- Active
Links
- 238000010438 heat treatment Methods 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000005286 illumination Methods 0.000 claims abstract description 24
- 238000012937 correction Methods 0.000 claims abstract description 14
- 239000000443 aerosol Substances 0.000 claims description 48
- 230000003287 optical effect Effects 0.000 claims description 26
- 238000002310 reflectometry Methods 0.000 claims description 23
- 230000008859 change Effects 0.000 claims description 20
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000002834 transmittance Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 208000006440 Open Bite Diseases 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims 2
- 239000000758 substrate Substances 0.000 claims 1
- 230000000694 effects Effects 0.000 description 6
- 239000003344 environmental pollutant Substances 0.000 description 5
- 231100000719 pollutant Toxicity 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000012855 volatile organic compound Substances 0.000 description 2
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 239000012080 ambient air Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 150000002894 organic compounds Chemical class 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 239000013618 particulate matter Substances 0.000 description 1
- 238000006303 photolysis reaction Methods 0.000 description 1
- 230000015843 photosynthesis, light reaction Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
Abstract
The invention discloses a method and a system for estimating NO2 concentration based on heating season, wherein the method comprises the following steps: dividing the map into a heating area and a non-heating area; identifying that the region to be estimated belongs to a heating region or a non-heating region; for the to-be-estimated belonging to the heating areaThe areas are divided into heating seasons and non-heating seasons according to heating time; predicting the average daily hour illumination of each grid of the region to be estimated for a period of time in the future through a solar illumination model; according to the predicted average day hour-by-hour illumination and the longitude and latitude of each grid of the region to be predicted, the method uses NO 2 Concentration estimation model for estimating NO of each grid for future period of time 2 Concentration; when the region to be estimated is a heating region, NO in the heating season is generated in the time interval 2 The predicted value of the concentration is combined with a heating season correction factor of the region to be predicted to correct and obtain NO combined with the heating season 2 And (5) estimating the concentration. The invention can obtain NO in a large range and full period 2 And (5) estimating the concentration.
Description
Technical Field
The invention relates to the technical field of atmosphere monitoring. In particular to a method and a system for estimating NO2 concentration based on heating seasons.
Background
The prediction and forecast of atmospheric pollutants are important information affecting future decisions of governments and residents as well as weather forecast. The method also has the same problems as weather forecast, especially the short-term (hour-day level) forecast of gaseous pollutants, which relates to the generation, transmission and process of the pollutants and comprises more complex physicochemical mechanisms, on the one hand, the existing forecast model can not fully consider all mechanisms of the production and transmission of the pollutants, and the forecast result is not accurate enough; on the other hand, the model itself is often too complex, requiring significant modeling and computational costs.
Existing satellite inversion near-ground NO 2 Concentration measurement mainly using satellite NO 2 Column concentration product junction surface NO 2 Observation data,Establishing machine learning statistical model by meteorological data, boundary layer height, land utilization type, DEM (digital elevation model), vegetation index, population data and the like to estimate satellite near-ground NO 2 Concentration. Extracting NO from ground site data and satellite data according to space-time matching rule 2 NDVI (normalized vegetation index), meteorological factors (temperature, atmospheric relative humidity, wind speed, near-ground atmospheric pressure, etc.), boundary layer height, land use type as model features, near-ground NO 2 The concentration is taken as a predicted target value. But in this way the resolution of near-surface concentration is lower; and because of adopting the polar orbit satellite, the transit time is short, and NO can not be monitored for 24 hours in the whole day 2 Near surface concentration conditions.
In the whole, NO set of hours-days scale NO which is convenient to configure and has accurate prediction result is not available 2 The pollutant prediction method (a track model needs to provide a large amount of pollution sources and related data in advance, the model configuration is difficult, a prediction model based on satellite remote sensing data cannot reach an hour level in time resolution, and a conventional prediction method based on ground observation site data needs to retrain the model frequently for a specific time period of a specific region so as to achieve a better effect).
The invention provides a NO based on time seasonal features and illuminance data 2 A prediction method.
Disclosure of Invention
The present invention has been made in view of the above-mentioned needs of the prior art, and is directed to NO 2 The problem that the concentration estimation is greatly influenced by seasons and heating or not is solved, and NO based on heating seasons is provided 2 Concentration estimation method and system.
In order to solve the problems, the invention is realized by adopting the following technical scheme:
NO based on heating season 2 The concentration estimation method comprises the following steps:
1) Map data are acquired, and a map is divided into a heating area and a non-heating area; identifying that the region to be estimated belongs to a heating region or a non-heating region, and dividing the region to be estimated into uniform grids;
2) For the regions to be estimated, which belong to the heating regions, dividing the regions into heating seasons and non-heating seasons according to heating time;
3) Predicting the average daily hour illumination of each grid of the region to be estimated for a period of time in the future through a solar illumination model;
4) According to the predicted average day hour-by-hour illumination and the longitude and latitude of each grid of the region to be predicted, the method uses NO 2 Concentration estimation model for estimating NO of each grid for future period of time 2 Concentration;
5) When the region to be estimated is a heating region, NO in the heating season is generated in the time interval 2 The predicted value of the concentration is combined with a heating season correction factor of the region to be predicted to correct and obtain NO combined with the heating season 2 And (5) estimating the concentration.
Optionally, the solar illuminance model is built by:
acquiring calendar weather data of a region to be estimated, hour-by-hour variation data of a satellite cloud picture, hour-by-hour variation data of aerosol optical thickness inverted by a satellite image and calendar day-by-hour illumination monitoring data, and interpolating the calendar weather data, the hour-by-hour variation data, the satellite image and the aerosol optical thickness inverted by the satellite image into each grid;
the method comprises the steps that calendar weather data of each grid, hour-by-hour variation data of satellite cloud pictures at corresponding time and aerosol optical thickness variation data inverted by satellite images are used as input; the solar illuminance model is obtained through training of a neural network by taking the illuminance data of each grid, which are obtained from the annual daily hours, as output.
Optionally, the calendar weather data includes: date, time, temperature, humidity, wind speed, weather status, PM2.5 value, and radiation intensity;
the hour-by-hour change data of the satellite cloud picture is obtained through satellite image data acquisition;
the satellite image inversion aerosol optical thickness change data is obtained by inversion through blue light wave band data and earth surface reflectivity data of the satellite image.
Optionally, processing the data prior to inputting the calendar weather data of each grid, the hour-by-hour variation data of the satellite cloud image at the corresponding time, and the aerosol optical thickness variation data of the satellite image inversion:
for a cloud occlusion region in the hour-by-hour change data of the satellite cloud picture, taking the cloud occlusion region of the satellite cloud picture as a main factor, inputting an input vector of a cloud occlusion quantized value in an input data sequence, and assigning a value of 0 to the cloud occlusion quantized value of a non-occlusion region;
for other areas of which the cloud body shielding area is removed, aerosol optical thickness change data is taken as a main factor; and inputting an input vector of an aerosol quantized value of aerosol optical thickness change data in the input data sequence, wherein the aerosol quantized value of the removed cloud shielding area is assigned to be 0.
Optionally, the cloud occlusion region is segmented by the following method:
converting the satellite image data into equal longitude and latitude coordinates, and interpolating into grids;
and according to the RGB values of each grid, a cloud body shielding region and other regions for removing the cloud body shielding region are obtained through segmentation by a threshold segmentation algorithm.
Optionally, the aerosol optical thickness variation data is obtained by:
converting the satellite image data into equal longitude and latitude coordinates, and interpolating into grids; acquiring surface reflectivity data of other areas except for the cloud shielding area;
sequentially setting the aerosol thickness of all grids to at least 9 grades, and establishing surface reflectivity data values corresponding to at least 9 grades; fitting to obtain a relation between the aerosol thickness file value and the earth surface reflectivity data value;
combining Rayleigh scattering, atmospheric hemispherical albedo, atmospheric downlink transmittance and atmospheric uplink transmittance, and comprehensively calculating to obtain apparent reflectivity corresponding to the satellite image;
taking apparent reflectivity obtained from satellite image data of each grid as an independent variable, and traversing the grids to obtain aerosol thickness file values of all grids by combining the relation between the aerosol thickness file values and the earth surface reflectivity data values;
and taking the sequence of the aerosol thickness file values of each grid corresponding to each hour as an input vector of aerosol optical thickness change data.
Alternatively, NO 2 The concentration estimation model is established by the following steps:
obtaining NO of a region to be estimated for a period of time 2 Concentration data, monitoring data of average day hour illumination of corresponding time and longitude and latitude of grids are used as training sets and test sets;
takes the average day hour illumination and the longitude and latitude of the grid as input, uses NO of corresponding time 2 The concentration data is used as output to respectively train to obtain NO in heating season and non-heating season 2 And (5) a concentration estimation model.
Alternatively, NO in heating and non-heating seasons according to the same solar illuminance condition with the grid 2 And (3) fitting the concentration difference and the relationship between the difference and the solar illuminance to obtain the heating season correction factor.
Optionally, correcting NO 2 The concentration predicted value comprises searching heating season correction factors according to the solar illuminance, and compensating the corresponding difference value to NO 2 And taking the predicted concentration value as a predicted result.
In a second aspect, the present invention also provides a heating season based NO2 concentration estimation system, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of any of the above methods when executing the computer program.
Compared with the prior art, the NO based on heating season of the invention 2 Concentration estimation method and system by dividing heating area and non-heating area and considering NO in heating area 2 NO as a result of changes in emissions and lifestyle 2 Concentration effects, solar illuminance corresponding to seasons, on NO 2 To estimate NO by differentiating heating or not by seasons 2 The accuracy of the calculated result is higher.
Drawings
Fig. 1 is a flow chart of a method for estimating NO2 concentration based on heating season according to an embodiment of the present invention.
Detailed Description
In order that the above-described aspects may be better understood, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Most of NO in atmosphere 2 Is formed by discharging NO and O 3 Generated after oxidation. Under enough illumination conditions, the organic compound reacts with volatile organic compounds VOCs to generate ozone and photochemical smog, secondary particulate matter pollution is initiated, and the PM2.5 pollution degree of the ambient air is aggravated. Whereas under light conditions NO 2 Can also be decomposed into NO and O 3 And NO in the heating season due to the fact that human activities in the heating season are more concentrated in the indoor and the emission difference of the heating burner in the heating season 2 Concentration prediction needs to consider factors of various human activities, so that comprehensive prediction based on the factors is difficult to realize accurately.
NO based on heating season of the embodiment of the invention 2 The concentration estimation method comprises the following steps:
1) Map data are acquired, and a map is divided into a heating area and a non-heating area; and identifying whether the region to be estimated belongs to a heating region or a non-heating region, and dividing the region to be estimated into uniform grids (5 km by 5 km).
2) And dividing the region to be estimated, which belongs to the heating region, into a heating season and a non-heating season according to the heating time.
3) And predicting the daily average hour illumination of each grid of the region to be estimated for a period of time in the future through a solar illumination model. The purpose of the hour-by-hour prediction of solar illuminance using the solar illuminance model is to consider the NO under the corresponding solar illuminance (irradiation intensity) condition 2 Speed of photolysis and response to humanInfluence of class activity, thereby influencing NO 2 Is a concentration of (3).
When in implementation, the solar illuminance model is established by the following steps:
the method comprises the steps of obtaining calendar weather data of a region to be estimated, hour-by-hour change data of a satellite cloud picture, hour-by-hour change data of aerosol optical thickness inverted by satellite images and calendar day-to-hour illumination monitoring data, and interpolating the obtained calendar weather data, the hour-by-hour change data of the satellite cloud picture, the hour-by-hour change data of aerosol optical thickness inverted by the satellite images and the calendar day-to-hour illumination monitoring data into grids. In practice, calendar weather data includes: date, time, temperature, humidity, wind speed, weather status, PM2.5 value, and radiation intensity; the hour-by-hour variation data of the satellite cloud image is obtained through satellite image data acquisition (GF-4 satellite image blue band data is used in the embodiment); the aerosol optical thickness variation data inverted by the satellite images are obtained by inversion through blue light wave band data and ground surface reflectivity (MOD 09A 1) data of the satellite images. And processing the data:
first, a cloud occlusion region is segmented:
converting the satellite image data into equal longitude and latitude coordinates, and interpolating into grids;
and according to the RGB values of each grid, a cloud body shielding region and other regions for removing the cloud body shielding region are obtained through segmentation by a threshold segmentation algorithm.
Then, assignment is performed:
and for the cloud occlusion region in the hour-by-hour change data of the satellite cloud picture, taking the cloud occlusion region of the satellite cloud picture as a main factor, inputting an input vector of a cloud occlusion quantized value in an input data sequence, and assigning a value of 0 to the cloud occlusion quantized value of the non-occlusion region.
For other areas of which the cloud body shielding area is removed, aerosol optical thickness change data is taken as a main factor; and inputting an input vector of an aerosol quantized value of aerosol optical thickness change data in the input data sequence, wherein the aerosol quantized value of the removed cloud shielding area is assigned to be 0.
In practice, the aerosol optical thickness variation data is obtained by the following steps:
converting the satellite image data into equal longitude and latitude coordinates, and interpolating into grids (GF-4 image space resolution 50 m); acquiring surface reflectivity data of other areas except for the cloud shielding area; the aerosol thickness of all grids is sequentially set to 9 grades (for example, 0.0005, 0.25, 0.5, 0.75, 1.0, 1.25, 1.5, 1.75 and 2.0), and 9 earth surface reflectivity data values corresponding to the 9 grades are established; fitting to obtain the relation between the aerosol thickness file value and the surface reflectivity data value. And combining Rayleigh scattering, atmospheric hemispherical albedo, atmospheric downlink transmittance and atmospheric uplink transmittance, and comprehensively calculating to obtain the apparent reflectivity corresponding to the satellite image. Taking the apparent reflectivity obtained by satellite image data calculation of each grid as an independent variable, and traversing the grids to obtain aerosol thickness file values of all grids by combining the relation between the aerosol thickness file values and the earth surface reflectivity data values; and taking the sequence of the aerosol thickness file values of each grid corresponding to each hour as an input vector of aerosol optical thickness change data.
In practice, the following formula can be used for calculation:
wherein:is apparent reflectance, +.>Is aerosol reflectivity, +.>Is the rayleigh scattering (rayleigh scattering),is the surface reflectivity; s is the atmospheric hemispherical albedo, +.>Is the atmospheric downlink transmittance, +.>Is the atmospheric uplink transmittance. />Is the result of satellite image radiometric calibration, +.>Using MOD09A1 surface reflectance data,、/>、S、/>、/>can be calculated from a 6S atmosphere model.
The method comprises the steps that calendar weather data of each grid, hour-by-hour variation data of satellite cloud pictures at corresponding time and aerosol optical thickness variation data inverted by satellite images are used as input; the solar illuminance model is obtained through training of a neural network by taking the illuminance data of each grid, which are obtained from the annual daily hours, as output.
4) According to the predicted average day hour-by-hour illumination and the longitude and latitude of each grid of the region to be predicted, the method uses NO 2 Concentration estimation model for estimating NO of each grid for future period of time 2 Concentration.
In practice, NO 2 The concentration estimation model is established by the following steps:
obtaining NO of a region to be estimated for a period of time 2 Concentration data, monitoring data of average day hour illumination of corresponding time and longitude and latitude of grids are used as training sets and test sets;
takes the average day hour illumination and the longitude and latitude of the grid as input, uses NO of corresponding time 2 The concentration data is used as output to respectively train to obtain NO in heating season and non-heating season 2 And (5) a concentration estimation model.
5) When to be estimatedThe region is a heating region, and the time interval is NO in heating season 2 The predicted value of the concentration is combined with a heating season correction factor of the region to be predicted to correct and obtain NO combined with the heating season 2 And (5) estimating the concentration.
In the implementation, NO in heating season and non-heating season is generated according to the same solar illuminance condition of the same grid 2 And (3) fitting the concentration difference and the relationship between the difference and the solar illuminance to obtain the heating season correction factor. Correction of NO 2 The concentration predicted value comprises searching heating season correction factors according to the solar illuminance, and compensating the corresponding difference value to NO 2 And taking the predicted concentration value as a predicted result.
The heating season correction factor is adopted, the numerical value of various complex influence factors is not needed to be considered, and only the result is reversely deduced, so that the correction value required by the result caused by the change of emission and human activities is approximately obtained, and a more accurate correction result can be obtained.
In a second aspect, the present invention also provides a heating season based NO2 concentration estimation system, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of any of the above methods when executing the computer program.
In conclusion, the invention can obtain NO which takes the comprehensive influence of solar illuminance into consideration under the conditions of different emission under heating and non-heating conditions and corresponding longitude, latitude and seasons under the condition of human living habit 2 Concentration. NO to achieve the desired region 2 And (5) estimating concentration. By dividing heating regions from non-heating regions and taking into account NO in the heating regions 2 Emission and human lifestyle changes, and solar illuminance versus NO for the corresponding season 2 To estimate and correct NO by differentiating heating from season to season 2 The accuracy of the estimated concentration is higher, and a large range of continuous NO per hour can be obtained 2 The concentration data of (2) overcomes the defect that the complete data cannot be obtained due to the short transit time and insufficient transit area of the polar orbit satellite, and can synthesize N of the whole period of the whole areaO 2 And (5) concentration prediction.
In the description of the present invention, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium; may be a communication between two elements or an interaction between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the present invention, unless expressly stated or limited otherwise, a first feature is "on" or "under" a second feature, which may be in direct contact with the first and second features, or in indirect contact with the first and second features via an intervening medium. Moreover, a first feature "above," "over" and "on" a second feature may be a first feature directly above or obliquely above the second feature, or simply indicate that the first feature is higher in level than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is level lower than the second feature.
In the description of the present specification, the terms "one embodiment," "some embodiments," "examples," "particular examples," or "some examples," etc., refer to particular features, structures, materials, or characteristics described in connection with the embodiment or example as being included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that alterations, modifications, substitutions and variations may be made in the above embodiments by those skilled in the art within the scope of the invention.
Claims (7)
1. NO based on heating season 2 The concentration estimation method is characterized by comprising the following steps:
1) Map data are acquired, and a map is divided into a heating area and a non-heating area; identifying that the region to be estimated belongs to a heating region or a non-heating region, and dividing the region to be estimated into uniform grids;
2) For the regions to be estimated, which belong to the heating regions, dividing the regions into heating seasons and non-heating seasons according to heating time;
3) Predicting the average daily hour illumination of each grid of the region to be estimated for a period of time in the future through a solar illumination model;
4) According to the predicted average day hour-by-hour illumination and the longitude and latitude of each grid of the region to be predicted, the method uses NO 2 Concentration estimation model for estimating NO of each grid for future period of time 2 Concentration; the NO 2 The concentration estimation model is established by the following steps:
obtaining NO of a region to be estimated for a period of time 2 Concentration data, monitoring data of average day hour illumination of corresponding time and longitude and latitude of grids are used as training sets and test sets;
the average day hour illumination and the longitude and latitude of the grid are used as input to correspond to the timeNO of the room 2 The concentration data is used as output to respectively train to obtain NO in heating season and non-heating season 2 A concentration estimation model;
5) When the region to be estimated is a heating region, NO in the heating season is generated in the time interval 2 The predicted value of the concentration is combined with a heating season correction factor of the region to be predicted to correct NO 2 A concentration prediction value comprising: searching a heating season correction factor according to the solar illuminance, and compensating the corresponding difference value to NO 2 On the predicted concentration value, NO in the heating season is corrected 2 Estimating the concentration;
wherein, according to NO in heating season and non-heating season under the same solar illumination condition of the same grid 2 And (3) fitting the concentration difference and the relationship between the difference and the solar illuminance to obtain the heating season correction factor.
2. The method of claim 1, wherein the solar illuminance model is established by:
acquiring calendar weather data of a region to be estimated, hour-by-hour variation data of a satellite cloud picture, hour-by-hour variation data of aerosol optical thickness inverted by a satellite image and calendar day-by-hour illumination monitoring data, and interpolating the calendar weather data, the hour-by-hour variation data, the satellite image and the aerosol optical thickness inverted by the satellite image into each grid;
the method comprises the steps that calendar weather data of each grid, hour-by-hour variation data of satellite cloud pictures at corresponding time and aerosol optical thickness variation data inverted by satellite images are used as input; the solar illuminance model is obtained through training of a neural network by taking the illuminance data of each grid, which are obtained from the annual daily hours, as output.
3. The method of claim 2, wherein the step of determining the position of the substrate comprises,
the calendar weather data includes: date, time, temperature, humidity, wind speed, weather status, PM2.5 value, and radiation intensity;
the hour-by-hour change data of the satellite cloud picture is obtained through satellite image data acquisition;
the satellite image inversion aerosol optical thickness variation data is obtained by inversion through blue light wave band data and earth surface reflectivity data of the satellite image.
4. A method according to claim 3, characterized in that the data are processed before being input with the calendar weather data of each grid, the hour-by-hour variation data of the satellite cloud map for the corresponding time and the aerosol optical thickness variation data of the satellite image inversion:
for a cloud occlusion region in the hour-by-hour change data of the satellite cloud picture, taking the cloud occlusion region of the satellite cloud picture as a main factor, inputting an input vector of a cloud occlusion quantization value in an input data sequence, and assigning a value of 0 to the cloud occlusion quantization value of a non-occlusion region;
for other areas of which the cloud body shielding area is removed, aerosol optical thickness change data is taken as a main factor; and inputting an input vector of an aerosol quantized value of aerosol optical thickness change data in the input data sequence, wherein the aerosol quantized value of the removed cloud shielding area is assigned to be 0.
5. The method of claim 4, wherein the cloud occlusion region is segmented by:
converting the satellite image data into equal longitude and latitude coordinates, and interpolating into grids;
and according to the RGB values of each grid, a cloud body shielding region and other regions for removing the cloud body shielding region are obtained through segmentation by a threshold segmentation algorithm.
6. The method of claim 4, wherein the aerosol optical thickness variation data is obtained by:
converting the satellite image data into equal longitude and latitude coordinates, and interpolating into grids; acquiring surface reflectivity data of other areas except for the cloud shielding area;
sequentially setting the aerosol thickness of all grids to at least 9 grades, and establishing surface reflectivity data values corresponding to at least 9 grades; fitting to obtain a relation between the aerosol thickness file value and the earth surface reflectivity data value;
combining Rayleigh scattering, atmospheric hemispherical albedo, atmospheric downlink transmittance and atmospheric uplink transmittance, and comprehensively calculating to obtain apparent reflectivity corresponding to the satellite image;
taking apparent reflectivity obtained from satellite image data of each grid as an independent variable, and traversing the grids to obtain aerosol thickness file values of all grids by combining the relation between the aerosol thickness file values and the earth surface reflectivity data values;
and taking the sequence of the aerosol thickness file values of each grid corresponding to each hour as an input vector of aerosol optical thickness change data.
7. NO based on heating season 2 A concentration estimation system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of the preceding claims 1 to 6 when executing the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311675528.4A CN117390971B (en) | 2023-12-08 | 2023-12-08 | Method and system for estimating NO2 concentration based on heating season |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311675528.4A CN117390971B (en) | 2023-12-08 | 2023-12-08 | Method and system for estimating NO2 concentration based on heating season |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117390971A CN117390971A (en) | 2024-01-12 |
CN117390971B true CN117390971B (en) | 2024-04-12 |
Family
ID=89472433
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311675528.4A Active CN117390971B (en) | 2023-12-08 | 2023-12-08 | Method and system for estimating NO2 concentration based on heating season |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117390971B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101382507B1 (en) * | 2012-10-19 | 2014-04-10 | 사단법인대기환경모델링센터 | Air quality forecast and management system |
CN110726653A (en) * | 2019-09-25 | 2020-01-24 | 中国电子科技集团公司第二十七研究所 | PM based on heaven and earth integration information2.5Concentration monitoring method |
WO2021099427A1 (en) * | 2019-11-22 | 2021-05-27 | Elichens | Method for estimating the concentration of analyte in air close to a route travelled by means of transport |
CN114898823A (en) * | 2022-07-01 | 2022-08-12 | 北京英视睿达科技股份有限公司 | High-spatial-temporal-resolution remote sensing near-surface NO 2 Concentration estimation method and system |
CN116167003A (en) * | 2023-02-17 | 2023-05-26 | 中国科学院南京地理与湖泊研究所 | Near-ground artificial source nitrogen dioxide high-definition product estimation method and system |
KR20230092435A (en) * | 2021-12-17 | 2023-06-26 | 주식회사 포스코 | Apparatus for monitoring air quality based on satellite and method thereof |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160091474A1 (en) * | 2014-09-29 | 2016-03-31 | Tanguy Griffon | Method and a System for Determining at Least One Forecasted Air Quality Health Effect Caused in a Determined Geographical Area by at Least One Air Pollutant |
-
2023
- 2023-12-08 CN CN202311675528.4A patent/CN117390971B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101382507B1 (en) * | 2012-10-19 | 2014-04-10 | 사단법인대기환경모델링센터 | Air quality forecast and management system |
CN110726653A (en) * | 2019-09-25 | 2020-01-24 | 中国电子科技集团公司第二十七研究所 | PM based on heaven and earth integration information2.5Concentration monitoring method |
WO2021099427A1 (en) * | 2019-11-22 | 2021-05-27 | Elichens | Method for estimating the concentration of analyte in air close to a route travelled by means of transport |
KR20230092435A (en) * | 2021-12-17 | 2023-06-26 | 주식회사 포스코 | Apparatus for monitoring air quality based on satellite and method thereof |
CN114898823A (en) * | 2022-07-01 | 2022-08-12 | 北京英视睿达科技股份有限公司 | High-spatial-temporal-resolution remote sensing near-surface NO 2 Concentration estimation method and system |
CN116167003A (en) * | 2023-02-17 | 2023-05-26 | 中国科学院南京地理与湖泊研究所 | Near-ground artificial source nitrogen dioxide high-definition product estimation method and system |
Non-Patent Citations (8)
Title |
---|
A land use regression application into simulating spatial distribution characteristics of particulate matter (PM2.5) concentration in city of Xi’an, China;Bin Guo等;Pol. J. Environ. Stud;20200520;4065-4076 * |
供暖排放对大气环境质量与人体健康影响的时空特征研究;李晗;中国博士学位论文全文数据库 工程科技Ⅰ辑;20230215;B027-160 * |
基于气态污染物的京津冀PM_(2.5)浓度模型研究;花家嘉;侯书勋;张婉莹;杨雨灵;孟凯;;环境科学与管理;20200215(第02期);37-41 * |
基于融合MODIS AOD和LME模型的京津冀地区PM_(2.5)季节浓度模拟;邵丝露;孙艳玲;马振兴;陈莉;毛健;高爽;张辉;付宏臣;景悦;;天津师范大学学报(自然科学版);20200930(第05期);54-62 * |
济南市大气污染物时空变化及预测分析;张亚茹;陈永金;郭庆春;孙浩;;环境工程;20200215(第02期);114-121 * |
通过模拟和地面多光谱测量实现大气透过率监测;王刚;光机电信息;19980215(第02期);4-7 * |
面向多源数据沈阳市PM2.5浓度预测研究及实证分析;齐甜方;蒋洪迅;石晓文;;系统工程;20180528(第05期);104-115 * |
香河地区冬季NO_2光解速率的变化特征及其估算方法的建立;杜超杰;赵舒曼;刘慧;马翼宁;邹嘉南;邓小波;胡波;;气候与环境研究;20200120(第01期);64-76 * |
Also Published As
Publication number | Publication date |
---|---|
CN117390971A (en) | 2024-01-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gharbia et al. | Spatially distributed potential evapotranspiration modeling and climate projections | |
CN110222475B (en) | Method for inverting moisture content of winter wheat plants based on multispectral remote sensing of unmanned aerial vehicle | |
Paredes et al. | Accuracy of daily estimation of grass reference evapotranspiration using ERA-Interim reanalysis products with assessment of alternative bias correction schemes | |
Bartók et al. | A climate projection dataset tailored for the European energy sector | |
CN115293473A (en) | Method for evaluating ecological restoration effect of forest grass | |
CN110927120B (en) | Early warning method for vegetation coverage | |
CN114019579B (en) | High space-time resolution near-surface air temperature reconstruction method, system and equipment | |
CN112580982B (en) | Ecological protection red line implementation evaluation based on multi-temporal remote sensing and CASA model | |
CN110896761A (en) | Irrigation decision-making method and system for greenhouse | |
Lian et al. | Sensitivity to the sources of uncertainties in the modeling of atmospheric CO 2 concentration within and in the vicinity of Paris | |
Pereira et al. | Solar irradiance modelling using an offline coupling procedure for the Weather Research and Forecasting (WRF) model | |
Flückiger et al. | Modelling daily air temperature at a fine spatial resolution dealing with challenging meteorological phenomena and topography in Switzerland | |
CN115375036A (en) | Crop maturity prediction method based on fusion of remote sensing and light energy utilization rate model and weather | |
CN115420690A (en) | Near-surface trace gas concentration inversion model and inversion method | |
Slingo et al. | Simulation of clear‐sky outgoing longwave radiation over the oceans using operational analyses | |
Xian | Analysis of impacts of urban land use and land cover on air quality in the Las Vegas region using remote sensing information and ground observations | |
CN117390971B (en) | Method and system for estimating NO2 concentration based on heating season | |
Xu et al. | Generating a high-resolution time-series ocean surface net radiation product by downscaling J-OFURO3 | |
CN114974453B (en) | High-coverage reconstruction method for atmospheric carbon dioxide column concentration | |
CN112990609B (en) | Air quality prediction method based on space-time bandwidth self-adaptive geographical weighted regression | |
Akdeniz | Spatio-temporal analysis of the effects of urban growth on urban heat island: Case of Konya, Turkiye | |
Ramírez-Beltrán et al. | A satellite algorithm for estimating relative humidity, based on GOES and MODIS satellite data | |
Nnah et al. | Geospatial assessment of urban heat island in Port Harcourt LGA, Rivers State, Nigeria | |
Nie et al. | Nonstationarity in the global terrestrial water cycle and its interlinkages in the Anthropocene | |
Arakida et al. | Regional-scale data assimilation with the Spatially Explicit Individual-based Dynamic Global Vegetation Model (SEIB-DGVM) over Siberia |
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 |