CN114330146A - Satellite gas data completion method and system - Google Patents
Satellite gas data completion method and system Download PDFInfo
- Publication number
- CN114330146A CN114330146A CN202210195200.1A CN202210195200A CN114330146A CN 114330146 A CN114330146 A CN 114330146A CN 202210195200 A CN202210195200 A CN 202210195200A CN 114330146 A CN114330146 A CN 114330146A
- Authority
- CN
- China
- Prior art keywords
- data
- satellite
- concentration
- gas
- wind speed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012549 training Methods 0.000 claims abstract description 45
- 238000013499 data model Methods 0.000 claims abstract description 33
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 53
- 230000009466 transformation Effects 0.000 claims description 50
- 238000003066 decision tree Methods 0.000 claims description 35
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 18
- 208000009989 Posterior Leukoencephalopathy Syndrome Diseases 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 7
- 239000001569 carbon dioxide Substances 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000007812 deficiency Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 abstract description 6
- 238000010801 machine learning Methods 0.000 abstract description 5
- 238000005259 measurement Methods 0.000 abstract description 2
- 230000001502 supplementing effect Effects 0.000 abstract description 2
- 239000007789 gas Substances 0.000 description 46
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 11
- 229910052799 carbon Inorganic materials 0.000 description 11
- CIWBSHSKHKDKBQ-JLAZNSOCSA-N Ascorbic acid Chemical compound OC[C@H](O)[C@H]1OC(=O)C(O)=C1O CIWBSHSKHKDKBQ-JLAZNSOCSA-N 0.000 description 10
- 230000002159 abnormal effect Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 238000007796 conventional method Methods 0.000 description 6
- ZZZCUOFIHGPKAK-UHFFFAOYSA-N D-erythro-ascorbic acid Natural products OCC1OC(=O)C(O)=C1O ZZZCUOFIHGPKAK-UHFFFAOYSA-N 0.000 description 5
- 229930003268 Vitamin C Natural products 0.000 description 5
- 235000019154 vitamin C Nutrition 0.000 description 5
- 239000011718 vitamin C Substances 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000002485 combustion reaction Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 238000007637 random forest analysis Methods 0.000 description 3
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 239000000356 contaminant Substances 0.000 description 2
- 238000011109 contamination Methods 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000029553 photosynthesis Effects 0.000 description 2
- 238000010672 photosynthesis Methods 0.000 description 2
- 238000013138 pruning Methods 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Images
Landscapes
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The disclosure relates to the field of gas measurement, in particular to a satellite gas data completion method and system. The method comprises the following steps: acquiring first gas information of a first satellite corresponding to the geographic coordinate, and acquiring second gas information of a second satellite corresponding to the geographic coordinate; matching the first gas information and the second gas information according to the geographic coordinates of the first satellite and the geographic coordinates of the second satellite, and simultaneously matching data such as corresponding meteorological factors, terrain, vegetation and the like to obtain a data set; training a machine learning model according to the data set so as to obtain a satellite data model of the first gas information supplemented by the second gas information; and supplementing the first gas information of the position by using the data model according to the second gas information of the preset position. The gas concentration in the monitoring missing area can be fully monitored, and meanwhile the accuracy of the gas concentration is guaranteed.
Description
Technical Field
The disclosure relates to the field of gas measurement, in particular to a satellite gas data completion method and system.
Background
Common satellites such as GOSAT (geostationary satellite), OCO-2 (orbiting carbon observation satellite), OCO-3 (orbiting carbon observation satellite), and the like currently monitor CO2The concentration width is only ten kilometers, and a large space range cannot be well covered. The current mainstream method mainly adopts a spatial interpolation method to directly process the original CO2And (4) performing interpolation on the concentration data, such as traditional methods of kriging interpolation, reverse distance weighted interpolation and the like. However, the final spatial resolution of the results obtained by these conventional methods is low, and is not suitable for the service requirement of a small area. In addition, the conventional method does not take into account meteorological field conditions and CO during satellite transit2The related pollution gas condition makes the obtained data have low precision.
Disclosure of Invention
The present disclosure is made based on the above-mentioned needs of the prior art, and the technical problem to be solved by the present disclosure is to provide a satellite gas data completion method and system, which can ensure the accuracy of the gas concentration in the monitoring missing region while completing the monitoring.
In order to solve the above problem, the technical solution provided by the present disclosure includes:
the satellite gas data completion method comprises the following steps: the preset area comprises a data acquisition area and a data lack area; the method is used for complementing the data of the data lack area by the data of the data acquisition area; acquiring first gas information of the data acquisition area through a first satellite; the first gas information comprises first concentration data and first coordinate information; acquiring second gas information of the data acquisition area through a second satellite; the second gas information comprises second concentration data and second coordinate information; acquiring meteorological data of the data acquisition area; acquiring digital elevation model data of the data acquisition area through a third satellite; performing space-time matching according to the first coordinate information and the second coordinate information to obtain a data set of the data acquisition area; constructing a data model from the dataset, the data model obtaining the first concentration data based at least on the second concentration data, the meteorological data, and the digital elevation model data.
Correlating the first gas information and the second gas information at the same geographic coordinates to train a machine learning model through the data set to complement the partially missing first gas information. And simultaneously, the condition of the meteorological field during the transit is taken into consideration to obtain the first gas information with higher precision.
Preferably, the first gas comprises CO2Said second gas comprising NO2And CO; the preset area is divided into a plurality of grids, the data set comprises sub data sets, each grid corresponds to one sub data set, and each sub data set comprises: CO22Concentration, NO2At least one of concentration, CO concentration, longitude, latitude, digital elevation model data, meteorological data, julian days; the meteorological data includes at least one of atmospheric relative humidity, atmospheric temperature, horizontal direction wind speed, vertical direction wind speed, total wind speed, and atmospheric pressure intensity.
By the above arrangement, multiple influences on CO2Concentration considerations are taken into account to improve the accuracy and accuracy of the prediction.
Preferably, the method further comprises processing the data set, wherein the processing comprises: is rejected in VCq∈(μ q -3δ q ，μ q +3δ q ) Out-of-range data where q ∈ [1,2,3 ]]，VC1Is CO2Concentration, VC2Is NO2Concentration, VC3As the concentration of CO,μ 1 CO acquired for a first satellite2The average value of the concentration is obtained,μ 2 NO acquired for second satellite2The average value of the concentration is obtained,μ 3 the mean CO concentration obtained for the second satellite,δ 1 CO acquired for a first satellite2The standard deviation of the concentration is shown in the specification,δ 2 NO acquired for second satellite2The standard deviation of the concentration is shown in the specification,δ 3 standard deviation of CO concentration obtained for the second satellite.
The interference of abnormal data on the machine learning model is eliminated, so that the final result is more accurate.
Preferably, the first coordinate is used as the referencePerforming space-time matching on the information and the second coordinate information, wherein the space-time matching comprises the following steps: based on the distance between the geographic coordinates of the first satellite and the geographic coordinates of the second satellitedWhether the value of (a) is within a threshold range determines whether the geographic coordinates of the first satellite and the geographic coordinates of the second satellite match; wherein
lon 1 Which represents the longitude of the first satellite or satellites,lon 2 which represents the longitude of the second satellite or satellites,lat 1 which represents the latitude of the first satellite or satellites,lat 2 indicating the latitude of the second satellite.
Establishing a link between the first gas information and the second gas information by geographic location. To improve the accuracy and accuracy of the prediction to some extent.
Preferably, the data set is subjected to feature transformation, and a data model is trained based on the data set subjected to feature transformation; the characteristic transformation comprises the steps of carrying out characteristic transformation on geographic coordinates to obtain LON = Ln (LON) and LAT = Ln (LAT), wherein LON is longitude data, and LAT is latitude data; and performing characteristic transformation on wind speed data in the vertical direction and the horizontal direction in meteorological data to obtain
Wherein WIND is the total WIND speed, U is the WIND speed in the horizontal direction, and V is the WIND speed in the vertical direction.
The implicit information in the features is extracted through feature transformation, so that the calculation process can be simplified to a certain extent, the calculation amount is reduced, and the accuracy of the result is improved.
Preferably, the data model includes: VC (vitamin C)1≌F(RH，TEMP，U，V，WIND，PRES，DEM，VC2，VC3LON, LAT, DOY) wherein CO2Concentration VC1The influence factors include atmospheric relative humidity RH, atmospheric temperature TEMP, horizontal direction WIND speed U and vertical direction WIND speed V, total WIND speed WIND, atmospheric pressure PRES, digital elevation model data DEM, NO2Concentration VC2、COConcentration VC3Longitude LON after feature transformation, latitude LAT after feature transformation and julian day DOY, F () are representing functions of the data model, and the digital elevation model data comprise landform and vegetation.
Preferably, the training of the data model based on the feature-transformed data set includes: dividing the data set after the characteristic transformation into a training set and a testing set; sampling the training set to obtain a plurality of samples; constructing a plurality of decision trees which are independent from each other by using the obtained sample as a training sample; the output carbon dioxide concentration is determined by a plurality of decision trees together.
The accuracy of the result is improved through the algorithm, the method is suitable for the input samples with multi-dimensional characteristics, and the method can be effectively operated on a large data set.
Preferably, the parameters of the number and the depth of the decision trees are adjusted by a grid search method.
The number and the depth of the decision trees are determined by a grid searching method so as to improve the precision.
Preferably, the data model trained from the training set is validated for accuracy by the test set.
Also provided is a satellite gas data completion system, including: the system comprises a presetting module, a data acquisition module and a data deficiency module, wherein the presetting module is used for presetting an area, and the presetting area comprises a data acquisition area and a data deficiency area; the module is used for complementing the data of the data lack area by the data of the data acquisition area; the first acquisition module acquires first gas information of the data acquisition area through a first satellite; the first gas information comprises first concentration data and first coordinate information; a second acquisition module that acquires second gas information of the data acquisition area via a second satellite; the second gas information comprises second concentration data and second coordinate information; a weather acquisition module for acquiring weather data of the data acquisition area; a third acquisition module that acquires digital elevation model data of the data acquisition area via a third satellite; the space-time matching module is used for performing space-time matching according to the first coordinate information and the second coordinate information to acquire a data set of the data acquisition area; and the data module is constructed according to the data set and obtains the first concentration data at least based on the second concentration data, the meteorological data and the digital elevation model data.
Correlating the first gas information and the second gas information at the same geographic coordinates to train a machine learning model through the data set to complement the partially missing first gas information. And simultaneously, the condition of the meteorological field during the transit is taken into consideration to obtain the first gas information with higher precision.
Preferably, the first gas comprises CO2Said second gas comprising NO2And CO; the preset area is divided into a plurality of grids, the data set comprises sub data sets, each grid corresponds to one sub data set, and each sub data set comprises: CO2 concentration, NO2At least one of concentration, CO concentration, longitude, latitude, digital elevation model data, meteorological data, julian days; the meteorological data includes at least one of atmospheric relative humidity, atmospheric temperature, horizontal direction wind speed, vertical direction wind speed, total wind speed, and atmospheric pressure intensity.
By the above arrangement, multiple influences on CO2Concentration considerations are taken into account to improve the accuracy and accuracy of the prediction.
Preferably, the system further comprises a data processing module: VC rejectionq∈(μ q -3δ q ，μ q +3δ q ) Out-of-range data where q ∈ [1,2,3 ]]，VC1Is CO2Concentration, VC2Is NO2Concentration, VC3As the concentration of CO,μ 1 CO acquired for a first satellite2The average value of the concentration is obtained,μ 2 NO acquired for second satellite2The average value of the concentration is obtained,μ 3 the mean CO concentration obtained for the second satellite,δ 1 CO acquired for a first satellite2The standard deviation of the concentration is shown in the specification,δ 2 is a secondNO acquired by satellite2The standard deviation of the concentration is shown in the specification,δ 3 standard deviation of CO concentration obtained for the second satellite.
The interference of abnormal data on the machine learning model is eliminated, so that the final result is more accurate.
Preferably, performing spatiotemporal matching according to the first coordinate information and the second coordinate information includes: based on the distance between the geographic coordinates of the first satellite and the geographic coordinates of the second satellitedWhether the value of (a) is within a threshold range determines whether the geographic coordinates of the first satellite and the geographic coordinates of the second satellite match; wherein
lon 1 Which represents the longitude of the first satellite or satellites,lon 2 which represents the longitude of the second satellite or satellites,lat 1 which represents the latitude of the first satellite or satellites,lat 2 indicating the latitude of the second satellite.
Establishing a link between the first gas information and the second gas information by geographic location. To improve the accuracy and accuracy of the prediction to some extent.
Preferably, the system further comprises a feature transformation module: training a data model based on the data set after the characteristic transformation; the characteristic transformation comprises the steps of carrying out characteristic transformation on geographic coordinates to obtain LON = Ln (LON) and LAT = Ln (LAT), wherein LON is longitude data, and LAT is latitude data; and performing characteristic transformation on wind speed data in the vertical direction and the horizontal direction in meteorological data to obtain
Wherein WIND is the total WIND speed, U is the WIND speed in the horizontal direction, and V is the WIND speed in the vertical direction.
The implicit information in the features is extracted through feature transformation, so that the calculation process can be simplified to a certain extent, the calculation amount is reduced, and the accuracy of the result is improved.
Preferably, the data model includes: VC (vitamin C)1≌F(RH，TEMP，U，V，WIND，PRES，DEM，VC2，VC3LON, LAT, DOY) wherein CO2Concentration VC1The influence factors include atmospheric relative humidity RH, atmospheric temperature TEMP, horizontal direction WIND speed U and vertical direction WIND speed V, total WIND speed WIND, atmospheric pressure PRES, digital elevation model data DEM, NO2Concentration VC2CO concentration VC3Longitude LON after feature transformation, latitude LAT after feature transformation and julian day DOY, F () are representing functions of the data model, and the digital elevation model data comprise landform and vegetation.
Preferably, training the data model based on the feature-transformed data set includes: dividing the data set after the characteristic transformation into a training set and a testing set; sampling the training set to obtain a plurality of samples; constructing a plurality of decision trees which are independent from each other by using the obtained sample as a training sample; the output carbon dioxide concentration is determined by a plurality of decision trees together.
The accuracy of the result is improved through the algorithm, the method is suitable for the input samples with multi-dimensional characteristics, and the method can be effectively operated on a large data set.
Preferably, the parameters of the number and the depth of the decision trees are adjusted by a grid search module.
The number and the depth of the decision trees are determined by a grid searching method so as to improve the precision.
Preferably, the system further comprises a verification module, and the verification module verifies the accuracy through a test set by using a data model obtained by training the training set.
Compared with the prior art, the method and the device have the advantages that the meteorological field condition of the satellite in transit and the CO are considered2Related pollution gas conditions, due to common satellite monitoring of CO2The concentration breadth is only ten kilometers, and can not well cover a large space range, and the whole China and even the global area CO can be supplemented through the method2Will help people to pass through the satellite CO2Concentration calculation of daily CO in target region2Flux to calculate CO for a specified period of time within the target area2And (4) discharging the amount. At the same time, canSupplemented CO2The data is used as an input parameter of a mode and can be used for quantitatively researching the global climate change problem. Finally, the complemented satellite CO can be combined2With other contaminants such as NO2CO, HCHO and the like, and brings great possibility for treating the carbon pollution at the same time.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present specification, and other drawings can be obtained by those skilled in the art according to the drawings.
Fig. 1 is a flowchart illustrating steps of a satellite gas data completion method according to an embodiment of the present disclosure;
fig. 2 is a flowchart illustrating a step S3 in a satellite gas data completion method according to an embodiment of the present disclosure;
FIG. 3 is an OCO-2 satellite raw observation CO in an embodiment of the disclosure2A concentration data profile;
FIG. 4 is a complemented CO obtained via a satellite data model in an embodiment of the disclosure2A concentration data profile;
FIG. 5 is a model predictive CO using methods in embodiments of the disclosure2Concentration and actual observed CO2Scatter plot of concentration.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the description of the embodiments of the present disclosure, it should be noted that, unless otherwise explicitly stated or limited, the term "connected" should be interpreted broadly, and may be, for example, a fixed connection, a detachable connection, or an integral connection, which may be a mechanical connection, an electrical connection, which may be a direct connection, or an indirect connection via an intermediate medium. The specific meaning of the above terms in the present disclosure can be understood by those of ordinary skill in the art as appropriate.
The terms "top," "bottom," "above … …," "below," and "on … …" as used throughout the description are relative positions with respect to components of the device, such as the relative positions of the top and bottom substrates inside the device. It will be appreciated that the devices are multifunctional, regardless of their orientation in space.
For the purpose of facilitating understanding of the embodiments of the present application, the following description will be made in terms of specific embodiments with reference to the accompanying drawings, which are not intended to limit the embodiments of the present application.
Example 1
Monitoring of CO due to currently common satellites such as GOSAT, OCO-2 and OCO-32The concentration width is only ten kilometers, and a large space range cannot be well covered. The resulting spatial resolution obtained by conventional methods is low to be applicable to small area prediction, and conventional methods do not combine the meteorological field conditions and CO2Taking into account the relevant contamination gas conditions leads to inaccurate final results.
In view of the above, the present embodiment provides a satellite gas supplementing method, referring to fig. 1 to 3. The gas comprises CO2。
The completion method comprises the following steps:
s1 obtaining influence CO2The concentration of (c).
The method comprises the steps that a preset area comprises a data acquisition area and a data lack area, and parameter data acquired by the data acquisition area supplements lack data of the data lack area. CO in a certain area2Is associated with a number of factors: temperature, humidity, air pressure, wind speed, etcFactor will be on CO2The distribution of (A) has an influence on the change of CO in the region2Concentration; the photosynthesis and respiration of the plant itself also affect CO2The distribution of vegetation and CO in the area can be seen2Has a close relationship with the concentration of (c).
The combustion of substances generates CO2In the case of incomplete combustion, part of NO is produced2NO and CO. In other words, NO2Concentration of NO and CO2There is also a certain correlation between the concentrations of (A) and (B).
The data acquired by the completion method of the present disclosure includes: only a dozen kilometers of CO in width due to limitation of the prior art2Concentration data; will be CO-mingled with CO2The relevant main factor is taken into consideration, namely the need to acquire NO2Concentration of CO, temperature, humidity, air pressure and wind speed. In addition, since the present disclosure needs to be expanded depending on geographic factors, digital elevation model data needs to be acquired, and the digital elevation model data includes terrain and vegetation distribution.
Further, the CO is obtained by observing the satellite OCO-2 through the orbital carbon2Concentration data; acquisition of NO by Sentinel 5P satellite (Sentinel-5P)2Concentration data of CO and concentration data of CO; acquiring data of atmospheric relative humidity RH, atmospheric temperature TEMP, wind speed U in the horizontal direction, wind speed V in the vertical direction and atmospheric pressure PRES through an European middle-term weather forecast center (ECMWF); and acquiring digital elevation model data through an earth observation satellite ALOS, wherein the data is the most initial data set. The data set comprises an atmospheric relative humidity RH, an atmospheric temperature TEMP, a wind speed U in the horizontal direction, a wind speed V in the vertical direction, an atmospheric pressure PRES, digital elevation model data DEM, a longitude lon and a latitude lat, NO2Concentration VC2Concentration of CO VC3，CO2Concentration VC1. The above-mentioned concentration may be a column concentration of satellites.
S2, the acquired data is processed, and the processing comprises removing abnormal values in the acquired data, extracting data matched in space and time and performing feature transformation on partial data.
For removing abnormal values in the acquired data, abnormal data needs to be removed because the acquired data may be unreasonable due to some situations in the data acquisition process.
The outliers include outliers in gas concentration data acquired by the satellite.
VCq∈(μ q -3δ q ，μ q +3δ q )
q∈[1,2,3]
When the gas concentration data acquired by the satellite is out of the range, the data is considered to be an abnormal value, wherein VC1Is CO2Concentration, VC2Is NO2Concentration, VC3As the concentration of CO,μ 1 CO acquired for a first satellite2The average value of the concentration is obtained,μ 2 NO acquired for second satellite2The average value of the concentration is obtained,μ 3 the mean CO concentration obtained for the second satellite,δ 1 CO acquired for a first satellite2The standard deviation of the concentration is shown in the specification,δ 2 NO acquired for second satellite2The standard deviation of the concentration is shown in the specification,δ 3 standard deviation of CO concentration obtained for the second satellite.
For extracting spatiotemporal matching data, a data set comprises multi-dimensional data from multiple sources, and in order to make the acquired data have certain relevance, a connection between the multi-dimensional data needs to be established. Furthermore, when information is acquired at a certain place, certain relation necessarily exists in the acquired data, so that the geographical position is used as a bridge, and the relation among the multi-dimensional data is established.
The preset area is divided into a plurality of grids, the data set comprises sub data sets, each grid corresponds to one sub data set, and each sub data set comprises: CO22Concentration, NO2At least one of concentration, CO concentration, longitude, latitude, digital elevation model data, meteorological data, julian days.
An exemplary Beijing is divided into N squares, each square is 7x7km, and each square corresponds to multiple parameters (CO) meeting matching requirements2Concentration, NO2Concentration, CO concentration, latitude and longitude, DEM, meteorological data (RH, TEMP, U, V, PRES)). The data set only matches a portion of the content in the result.
Further, the orbital carbon observation satellite OCO-2 is used for observing CO at a certain place2The concentration is collected, and the Sentinel-5P satellite is used for collecting NO at a certain place2And (3) collecting the concentration and the CO concentration, and judging whether the geographic positions of the two places are matched by the following expressions:
whereinlon 1 Represents the longitude of the orbiting carbon observation satellite OCO-2,lon 1 indicates the longitude of the Sentinel-5P satellite,lat 1 represents the latitude of the orbit carbon observation satellite OCO-2,lat 2 indicates the latitude of the Sentinel-5P satellite whendAnd when the angle is less than or equal to 0.01 DEG, the data of the first satellite and the data of the second satellite are the same-position data.
The judgment of the places of other dimension data is the same as the judgment process, and the relationship among the multidimensional data is established through mutual judgment of every two dimension data, so that a data set with certain regionality is obtained.
And performing feature transformation on part of data, wherein the feature transformation is to perform certain transformation on the features and extract implicit information and the like.
The data subjected to the feature transformation includes longitude and latitude data, and wind speed data in the horizontal direction and wind speed data in the vertical direction.
For feature transformation of longitude and latitude, it is expressed as:
LON=ln(lon)
LAT=ln(lat)
the feature transformation for wind speed data in the horizontal direction and wind speed data in the vertical direction is expressed as:
wherein,WINDis the total wind speed.
S3 training a machine model based on the data set to obtain the NO2And CO whose concentration is complemented2A satellite data model of concentration; said NO according to a predetermined position2And the concentration of CO, complementing the CO at the location using the data model2Concentration the data set includes a training set and a test set, and the data set is calculated according to the following formula of 7: the ratio of 3 is randomly divided into a training set and a test set.
S301 performs a back sampling on the training set to obtain a plurality of sample sets.
Specifically, the sample set has N data, and N data are randomly extracted as samples each time the data is replaced from the original training set.
S302, a decision tree is constructed through the samples and the multi-dimensional features.
The sample is multi-dimensional data, each dimension is a feature, m features are randomly extracted from the multiple features to serve as candidate features of decision making under a previous node, and features for best dividing training samples are selected from the features. And (3) constructing a decision tree by taking each sample set as a training sample, and calculating by using a CART algorithm after the sample set and the determined characteristics are generated by a single decision tree without pruning.
S303, the decision trees perform decision making and then act together to output results.
After the required number of decision trees is obtained, voting is carried out on the output of the decision trees, and the class with the most votes is taken as the output, namely the concentration of the supplemented carbon dioxide is expressed as:
VC1≌F(RH，TEMP，U，V，WIND，PRES，DEM，VC2，VC3，LON，LAT，DOY)
wherein CO is2Concentration VC1The influence factors include the relative humidity RH of the atmosphere, the temperature TEMP of the atmosphere, the wind speed U in the horizontal direction, the wind speed V in the vertical direction and the total wind speed WIND, atmospheric pressure PRES, digital elevation model data DEM, NO2Concentration VC2CO concentration VC3Longitude after feature transformation LON, latitude after feature transformation LAT and julian day DOY, F () are the representation functions of the data model.
By adopting the method, the training samples are sampled, and the features are sampled, so that the independence of each constructed tree is fully ensured, and the voting result is more accurate. The training samples for each decision tree are random and the splitting attribute for each node in the tree is also randomly selected. With these two random factors, no overfitting occurs even if each decision tree is not pruned.
In the CART algorithm, the generation of the CART decision tree is a process of recursively constructing a binary decision tree. CART decision trees can be used for both classification and regression. For the decision tree for classification, CART uses Gini coefficient minimization criterion to select features, generating a binary tree.
The CART generation algorithm is as follows:
according to the training data set, from a root node, recursively carrying out the following operations on each node to construct a binary decision tree:
and (4) setting the training data set of the nodes as D, and calculating the Gini coefficient of the existing characteristics to the data set. At this time, for each feature a, for each value a that it is possible to take, D is divided into two parts, D1 and D2, according to whether the test of the sample point pair a = a is yes or no, and the Gini coefficient at a = a is calculated.
And selecting the feature with the minimum Gini coefficient and the corresponding segmentation point thereof as the optimal feature and the optimal segmentation point from all the possible features A and all the possible segmentation points a thereof. And generating two sub-nodes from the current node according to the optimal characteristics and the optimal segmentation points, and distributing the training data set into the two sub-nodes according to the characteristics.
And generating the CART decision tree until a stopping condition is met.
And adjusting two parameters of the number and the depth of the decision tree by a grid searching method. The grid search method is an exhaustive search method for specified parameter values, and an optimal learning algorithm is obtained by optimizing parameters of an estimation function through a cross validation method.
In all candidate parameter selections, each possibility is tried through loop traversal, and the best performing parameter is the final result. A smaller domain of hyper-parameters is listed, and the Cartesian products (permutation and combination) of the hyper-parameters are a set of hyper-parameters. The grid search algorithm trains the model using each set of hyper-parameters and picks the hyper-parameter combination with the smallest error in the validation set.
S4, the accuracy of the satellite gas completion data model obtained by training the training set is verified through the testing set.
Illustratively, referring to FIG. 3, FIG. 3 shows a 2-month 2-day satellite OCO-2 CO of 20202Raw observation data distribution, in which the diagram stacked by a plurality of points in a discontinuous stripe distribution in the diagram is CO2Raw observation data. The satellite data model obtained by the method provided by the embodiment can convert CO into CO2The concentration is supplemented to the whole China, and refer to FIG. 4. This is for global CO2The influence of greenhouse gases on global warming effect brings about more scientific and quantitative evaluation.
Referring to FIG. 5, FIG. 5 shows the CO of the OCO-2 satellite in the test set (randomly selected 30% of the data in the sample set)2Actual observed concentration (x-axis) and CO predicted by random forest model2Scatter verification between concentrations (y-axis). Wherein the test set data volume is 152637, R2The random forest model is 0.93, the root mean square error RMSE is 0.85ppm, the average absolute error MAE is 0.77ppm, and the data show that the random forest model applied by the invention is used for satellite CO2The completion has higher precision and very reliable result.
For satellite CO2The completion can ensure that the whole China even the global area CO2The space coverage is greatly improved, which is helpful for people to pass through the satellite CO2Concentration calculation of daily CO in target region2Flux to calculate CO for a specified period of time within the target area2And (4) discharging the amount. Meanwhile, the supplemented CO can be used2The data is used as input parameters of the model and can be used for quantitative researchThe problem of global climate change is solved. Finally, the complemented satellite CO can be combined2With other contaminants such as NO2CO, HCHO and the like, and brings great possibility for treating the carbon pollution at the same time.
Example 2
Monitoring of CO due to currently common satellites such as GOSAT, OCO-2 and OCO-32The concentration width is only ten kilometers, and a large space range cannot be well covered. The resulting spatial resolution obtained by conventional methods is low to be applicable to small area prediction, and conventional methods do not combine the meteorological field conditions and CO2Taking into account the relevant contamination gas conditions leads to inaccurate final results.
In view of the above, the present embodiment provides a satellite gas data completion system, wherein the gas includes CO2。
The system comprises an acquisition module, a data processing module, a matching module and a data module.
The system supplements the lack data of the data lack area through the parameter data acquired by the data acquisition area. CO in a certain area2Is associated with a number of factors: temperature, humidity, air pressure and wind speed will contribute to CO2The distribution of (A) has an influence on the change of CO in the region2Concentration; the photosynthesis and respiration of the plant itself also affect CO2The distribution of vegetation and CO in the area can be seen2Has a close relationship with the concentration of (c).
The combustion of substances generates CO2In the case of incomplete combustion, part of NO is produced2NO and CO. In other words, NO2Concentration of NO and CO2There is also a certain correlation between the concentrations of (A) and (B).
The acquisition module comprises a first acquisition module, a second acquisition module, a third acquisition module and a weather acquisition module.
Only a dozen kilometers of CO in width due to limitation of the prior art2Concentration data; will be CO-mingled with CO2The relevant main factor is taken into consideration, namely the need to acquire NO2Concentration of CO, temperature, humidity, air pressure and wind speed. In addition, since the present disclosure needs to be expanded depending on geographic factors, digital elevation model data needs to be acquired, and the digital elevation model data includes terrain and vegetation distribution.
The first acquisition module acquires CO through an orbital carbon observation satellite OCO-22Concentration data; the second acquisition module acquires NO through Sentinel 5P satellite (Sentinel-5P)2Concentration data of CO and concentration data of CO; the weather obtaining module obtains data of atmospheric relative humidity RH, atmospheric temperature TEMP, wind speed U in the horizontal direction, wind speed V in the vertical direction and atmospheric pressure PRES through an European middle weather forecast center (ECMWF); the third acquisition module acquires digital elevation model data through an earth observation satellite ALOS, wherein the data is the most initial data set. The data set comprises an atmospheric relative humidity RH, an atmospheric temperature TEMP, a wind speed U in the horizontal direction, a wind speed V in the vertical direction, an atmospheric pressure PRES, digital elevation model data DEM, a longitude lon and a latitude lat, NO2Concentration VC2Concentration of CO VC3，CO2Concentration VC1。
A data processing module for performing data processing on the data set. In the data acquisition process, the situation that the obtained data is unreasonable may occur due to some situations, and abnormal data needs to be removed.
The outliers include outliers in gas concentration data acquired by the satellite.
VCq∈(μ q -3δ q ，μ q +3δ q )
q∈[1,2,3]
When the gas concentration data acquired by the satellite is out of the range, the data is considered to be an abnormal value, wherein VC1Is CO2Concentration, VC2Is NO2Concentration, VC3As the concentration of CO,μ 1 CO acquired for a first satellite2The average value of the concentration is obtained,μ 2 NO acquired for second satellite2The average value of the concentration is obtained,μ 3 the mean CO concentration obtained for the second satellite,δ 1 CO acquired for a first satellite2The standard deviation of the concentration is shown in the specification,δ 2 NO acquired for second satellite2The standard deviation of the concentration is shown in the specification,δ 3 standard deviation of CO concentration obtained for the second satellite.
In order to obtain data with a certain relevance, a relation between data of multiple dimensions needs to be established. The connection is realized by the matching module, and when information is acquired at a certain place, certain connection necessarily exists in the acquired data, so that the geographical position is used as a bridge to establish the connection among the multi-dimensional data. The above functions are realized by a space-time matching module.
The preset area is divided into a plurality of grids, the data set comprises sub data sets, each grid corresponds to one sub data set, and each sub data set comprises: CO22Concentration, NO2At least one of concentration, CO concentration, longitude, latitude, digital elevation model data, meteorological data, julian days.
An exemplary Beijing is divided into N squares, each square is 7x7km, and each square corresponds to multiple parameters (CO) meeting matching requirements2Concentration, NO2Concentration, CO concentration, latitude and longitude, DEM, meteorological data (RH, TEMP, U, V, PRES)). The data set only matches a portion of the content in the result.
Further, the orbital carbon observation satellite OCO-2 is used for observing CO at a certain place2The concentration is collected, and the Sentinel-5P satellite is used for collecting NO at a certain place2And (3) collecting the concentration and the CO concentration, and judging whether the geographic positions of the two places are matched by the following expressions:
whereinlon 1 Represents the longitude of the orbiting carbon observation satellite OCO-2,lon 2 indicates the longitude of the Sentinel-5P satellite,lat 1 represents the latitude of the orbit carbon observation satellite OCO-2,lat 2 indicates the latitude of the Sentinel-5P satellite whendAnd when the angle is less than or equal to 0.01 DEG, the data of the first satellite and the data of the second satellite are the same-position data.
The judgment of the places of other dimension data is the same as the judgment process, and the relationship among the multidimensional data is established through mutual judgment of every two dimension data, so that a data set with certain regionality is obtained.
And the characteristic transformation module is used for carrying out certain transformation on the characteristics and extracting implicit information and the like. The characteristics are the dimensionality of the data in the data set, including the atmospheric relative humidity RH, the atmospheric temperature TEMP, the wind speed U in the horizontal direction, the wind speed V in the vertical direction, the atmospheric pressure PRES, the digital elevation model data DEM, the longitude lon, the latitude lat and the NO2Concentration VC2Concentration of CO VC3，CO2Concentration VC1。
The data subjected to the feature transformation includes longitude and latitude data, and wind speed data in the horizontal direction and wind speed data in the vertical direction.
For feature transformation of longitude and latitude, it is expressed as:
LON=ln(lon)
LAT=ln(lat)
the feature transformation for wind speed data in the horizontal direction and wind speed data in the vertical direction is expressed as:
wherein,WINDis the total wind speed.
The data module comprises a sampling module, a decision tree module and an output module.
A sampling module that samples the training set with the put back to obtain a plurality of sample sets. Specifically, the sample set has N data, and N data are randomly extracted as samples each time the data is replaced from the original training set.
And the decision tree module is used for randomly extracting m features from a plurality of features as candidate features for decision making under the previous node, and selecting the features for best dividing the training sample from the features. And (3) constructing a decision tree by taking each sample set as a training sample, and calculating by using a CART algorithm after the sample set and the determined characteristics are generated by a single decision tree without pruning.
An output module, which votes the outputs of the decision tree modules to take the class with the most votes as the output, namely the concentration of the complemented carbon dioxide, and is expressed as:
VC1≌F(RH，TEMP，U，V，WIND，PRES，DEM，VC2，VC3，LON，LAT，DOY)
wherein CO is2Concentration VC1The influence factors include atmospheric relative humidity RH, atmospheric temperature TEMP, horizontal direction WIND speed U and vertical direction WIND speed V, total WIND speed WIND, atmospheric pressure PRES, digital elevation model data DEM, NO2Concentration VC2CO concentration VC3Longitude after feature transformation LON, latitude after feature transformation LAT and julian day DOY, F () are the representation functions of the data model.
And the grid searching module is used for adjusting the two parameters of the number and the depth of the decision trees. The grid search method is an exhaustive search method for specified parameter values, and an optimal learning algorithm is obtained by optimizing parameters of an estimation function through a cross validation method.
And the verification module is used for verifying the accuracy of the data module obtained by training the training set through the test set.
The above-mentioned embodiments, objects, technical solutions and advantages of the present application are described in further detail, it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present application, and are not intended to limit the scope of the present application, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present application should be included in the scope of the present application.
Claims (18)
1. A satellite gas data completion method, comprising:
the preset area comprises a data acquisition area and a data lack area; the method is used for complementing the data of the data lack area by the data of the data acquisition area;
acquiring first gas information of the data acquisition area through a first satellite; the first gas information comprises first concentration data and first coordinate information;
acquiring second gas information of the data acquisition area through a second satellite; the second gas information comprises second concentration data and second coordinate information;
acquiring meteorological data of the data acquisition area;
acquiring digital elevation model data of the data acquisition area through a third satellite;
performing space-time matching according to the first coordinate information and the second coordinate information to obtain a data set of the data acquisition area;
constructing a data model from the dataset, the data model obtaining the first concentration data based at least on the second concentration data, the meteorological data, and the digital elevation model data.
2. The satellite gas data completion method according to claim 1,
the first gas comprises CO2Said second gas comprising NO2And CO;
the preset area is divided into a plurality of grids, the data set comprises sub data sets, each grid corresponds to one sub data set, and each sub data set comprises: CO22Concentration, NO2Concentration, CO concentration, longitude, latitude, digital elevation model data, meteorological dataAt least one of julian days;
the meteorological data includes at least one of atmospheric relative humidity, atmospheric temperature, horizontal direction wind speed, vertical direction wind speed, total wind speed, and atmospheric pressure intensity.
3. The satellite gas data completion method according to claim 2, further comprising processing the data set, wherein the processing comprises:
is rejected in VCq∈(μ q -3δ q ，μ q +3δ q ) Out-of-range data where q ∈ [1,2,3 ]]，VC1Is CO2Concentration, VC2Is NO2Concentration, VC3As the concentration of CO,μ 1 CO acquired for a first satellite2The average value of the concentration is obtained,μ 2 NO acquired for second satellite2The average value of the concentration is obtained,μ 3 the mean CO concentration obtained for the second satellite,δ 1 CO acquired for a first satellite2The standard deviation of the concentration is shown in the specification,δ 2 NO acquired for second satellite2The standard deviation of the concentration is shown in the specification,δ 3 standard deviation of CO concentration obtained for the second satellite.
4. The satellite gas data completion method according to claim 1, wherein the performing the space-time matching according to the first coordinate information and the second coordinate information includes: based on the distance between the geographic coordinates of the first satellite and the geographic coordinates of the second satellitedWhether the value of (a) is within a threshold range determines whether the geographic coordinates of the first satellite and the geographic coordinates of the second satellite match; wherein
lon 1 Which represents the longitude of the first satellite or satellites,lon 2 which represents the longitude of the second satellite or satellites,lat 1 which represents the latitude of the first satellite or satellites,lat 2 indicating the latitude of the second satellite.
5. The satellite gas data completion method according to claim 3 or 4, wherein the method further comprises:
performing characteristic transformation on the data set, and training a data model based on the data set after the characteristic transformation;
the characteristic transformation comprises the steps of carrying out characteristic transformation on geographic coordinates to obtain LON = Ln (LON) and LAT = Ln (LAT), wherein LON is longitude data, and LAT is latitude data; and performing characteristic transformation on wind speed data in the vertical direction and the horizontal direction in meteorological data to obtain
Wherein WIND is the total WIND speed, U is the WIND speed in the horizontal direction, and V is the WIND speed in the vertical direction.
6. The satellite gas data completion method according to claim 5, wherein the data model comprises:
VC1≌F(RH，TEMP，U，V，WIND，PRES，DEM，VC2，VC3，LON，LAT，DOY)
wherein CO is2Concentration VC1The influence factors include atmospheric relative humidity RH, atmospheric temperature TEMP, horizontal direction WIND speed U and vertical direction WIND speed V, total WIND speed WIND, atmospheric pressure PRES, digital elevation model data DEM, NO2Concentration VC2CO concentration VC3Longitude LON after feature transformation, latitude LAT after feature transformation and julian day DOY, F () are representing functions of the data model, and the digital elevation model data comprise landform and vegetation.
7. The satellite gas data completion method according to claim 6, wherein the training of the data model based on the feature-transformed data set comprises:
dividing the data set after the characteristic transformation into a training set and a testing set;
sampling the training set to obtain a plurality of samples;
constructing a plurality of decision trees which are independent from each other by using the obtained sample as a training sample;
the output carbon dioxide concentration is determined by a plurality of decision trees together.
8. The satellite gas data completion method according to claim 7, wherein parameters of the number and depth of the decision trees are adjusted by a grid search method.
9. The satellite gas data completion method according to claim 8, wherein the data model trained by the training set is verified for accuracy by the testing set.
10. A satellite gas data completion system, comprising:
the system comprises a presetting module, a data acquisition module and a data deficiency module, wherein the presetting module is used for presetting an area, and the presetting area comprises a data acquisition area and a data deficiency area; the module is used for complementing the data of the data lack area by the data of the data acquisition area;
the first acquisition module acquires first gas information of the data acquisition area through a first satellite; the first gas information comprises first concentration data and first coordinate information;
a second acquisition module that acquires second gas information of the data acquisition area via a second satellite; the second gas information comprises second concentration data and second coordinate information;
a weather acquisition module for acquiring weather data of the data acquisition area;
a third acquisition module that acquires digital elevation model data of the data acquisition area via a third satellite;
the space-time matching module is used for performing space-time matching according to the first coordinate information and the second coordinate information to acquire a data set of the data acquisition area;
and the data module is constructed according to the data set and obtains the first concentration data at least based on the second concentration data, the meteorological data and the digital elevation model data.
11. The satellite gas data completion system according to claim 10,
the first gas comprises CO2Said second gas comprising NO2And CO;
the preset area is divided into a plurality of grids, the data set comprises sub data sets, each grid corresponds to one sub data set, and each sub data set comprises: CO2 concentration, NO2At least one of concentration, CO concentration, longitude, latitude, digital elevation model data, meteorological data, julian days;
the meteorological data includes at least one of atmospheric relative humidity, atmospheric temperature, horizontal direction wind speed, vertical direction wind speed, total wind speed, and atmospheric pressure intensity.
12. The satellite gas data completion system according to claim 11, further comprising a data processing module:
is rejected in VCq∈(μ q -3δ q ，μ q +3δ q ) Out-of-range data where q ∈ [1,2,3 ]]，VC1Is CO2Concentration, VC2Is NO2Concentration, VC3As the concentration of CO,μ 1 CO acquired for a first satellite2The average value of the concentration is obtained,μ 2 NO acquired for second satellite2The average value of the concentration is obtained,μ 3 the mean CO concentration obtained for the second satellite,δ 1 CO acquired for a first satellite2The standard deviation of the concentration is shown in the specification,δ 2 NO acquired for second satellite2The standard deviation of the concentration is shown in the specification,δ 3 standard deviation of CO concentration obtained for the second satellite.
13. The satellite gas data completion system according to claim 10, wherein performing spatiotemporal matching based on said first coordinate information and said second coordinate information comprises: based on the distance between the geographic coordinates of the first satellite and the geographic coordinates of the second satellitedWhether the value of (a) is within a threshold range determines whether the geographic coordinates of the first satellite and the geographic coordinates of the second satellite match; wherein
lon 1 Which represents the longitude of the first satellite or satellites,lon 2 which represents the longitude of the second satellite or satellites,lat 1 which represents the latitude of the first satellite or satellites,lat 2 indicating the latitude of the second satellite.
14. The satellite gas data completion system according to claim 12 or 13, wherein said system further comprises a feature transformation module:
training a data model based on the data set after the characteristic transformation;
the characteristic transformation comprises the steps of carrying out characteristic transformation on geographic coordinates to obtain LON = Ln (LON) and LAT = Ln (LAT), wherein LON is longitude data, and LAT is latitude data; and performing characteristic transformation on wind speed data in the vertical direction and the horizontal direction in meteorological data to obtain
Wherein WIND is the total WIND speed, U is the WIND speed in the horizontal direction, and V is the WIND speed in the vertical direction.
15. The satellite gas data completion system according to claim 14, wherein said data model comprises:
VC1≌F(RH，TEMP，U，V，WIND，PRES，DEM，VC2，VC3，LON，LAT，DOY)
wherein CO is2Concentration VC1The influence factors include atmospheric relative humidity RH, atmospheric temperature TEMP, horizontal direction WIND speed U and vertical direction WIND speed V, total WIND speed WIND, atmospheric pressure PRES, digital elevation model data DEM, NO2Concentration VC2CO concentration VC3Longitude LON after feature transformation, latitude LAT after feature transformation and julian day DOY, F () are representing functions of the data model, and the digital elevation model data comprise landform and vegetation.
16. The satellite gas data completion system according to claim 15, wherein said training data model based on said feature transformed data set comprises:
dividing the data set after the characteristic transformation into a training set and a testing set;
sampling the training set to obtain a plurality of samples;
constructing a plurality of decision trees which are independent from each other by using the obtained sample as a training sample;
the output carbon dioxide concentration is determined by a plurality of decision trees together.
17. The satellite gas data completion system according to claim 16, wherein parameters of the number and depth of said decision trees are adjusted by a grid search module.
18. The satellite gas data completion system according to claim 17, further comprising a verification module, wherein said verification module verifies accuracy of said data model from said training set through said testing set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210195200.1A CN114330146B (en) | 2022-03-02 | 2022-03-02 | Satellite gas data completion method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210195200.1A CN114330146B (en) | 2022-03-02 | 2022-03-02 | Satellite gas data completion method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114330146A true CN114330146A (en) | 2022-04-12 |
| CN114330146B CN114330146B (en) | 2022-06-28 |
Family
ID=81031105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210195200.1A Active CN114330146B (en) | 2022-03-02 | 2022-03-02 | Satellite gas data completion method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114330146B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117113089A (en) * | 2023-10-16 | 2023-11-24 | 北京英视睿达科技股份有限公司 | Methane data complement method, device, equipment and medium based on carbon monoxide |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180231515A1 (en) * | 2015-08-13 | 2018-08-16 | Take Off Diffusion S.A. | Gas measurement device incorporated into a watch |
| CN109344865A (en) * | 2018-08-24 | 2019-02-15 | 山东省环境规划研究院 | A kind of data fusion method of multi-data source |
| CN111443163A (en) * | 2020-03-10 | 2020-07-24 | 中国科学院深圳先进技术研究院 | Interpolation method and device for ozone missing data and interpolation equipment |
| CN112016696A (en) * | 2020-08-14 | 2020-12-01 | 武汉大学 | PM integrating satellite observation and ground observation1Concentration inversion method and system |
| CN113297528A (en) * | 2021-06-10 | 2021-08-24 | 四川大学 | NO based on multi-source big data2High-resolution space-time distribution calculation method |
-
2022
- 2022-03-02 CN CN202210195200.1A patent/CN114330146B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180231515A1 (en) * | 2015-08-13 | 2018-08-16 | Take Off Diffusion S.A. | Gas measurement device incorporated into a watch |
| CN109344865A (en) * | 2018-08-24 | 2019-02-15 | 山东省环境规划研究院 | A kind of data fusion method of multi-data source |
| CN111443163A (en) * | 2020-03-10 | 2020-07-24 | 中国科学院深圳先进技术研究院 | Interpolation method and device for ozone missing data and interpolation equipment |
| CN112016696A (en) * | 2020-08-14 | 2020-12-01 | 武汉大学 | PM integrating satellite observation and ground observation1Concentration inversion method and system |
| CN113297528A (en) * | 2021-06-10 | 2021-08-24 | 四川大学 | NO based on multi-source big data2High-resolution space-time distribution calculation method |
Non-Patent Citations (4)
| Title |
|---|
| STEVEN A. ACKERMAN等: "Discriminating clear sky from clouds with MODIS", 《JOURNAL OF GEOPHYSICAL RESEARCH》 * |
| 吕松等: "地表高程对大气CO_2反演的影响", 《光学学报》 * |
| 徐彬仁等: "中国海洋上空细粒子气溶胶与短寿命痕量气体的时空关系", 《遥感学报》 * |
| 曹良中等: "中亚近地面CO2浓度时空分布及驱动因子分析", 《遥感信息》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117113089A (en) * | 2023-10-16 | 2023-11-24 | 北京英视睿达科技股份有限公司 | Methane data complement method, device, equipment and medium based on carbon monoxide |
| CN117113089B (en) * | 2023-10-16 | 2024-01-23 | 北京英视睿达科技股份有限公司 | Methane data complement method, device, equipment and medium based on carbon monoxide |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114330146B (en) | 2022-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230213337A1 (en) | Large-scale forest height remote sensing retrieval method considering ecological zoning | |
| Reuter et al. | A joint effort to deliver satellite retrieved atmospheric CO 2 concentrations for surface flux inversions: the ensemble median algorithm EMMA | |
| Jiménez et al. | Exploring the merging of the global land evaporation WACMOS-ET products based on local tower measurements | |
| Gupta et al. | Machine learning algorithm for estimating surface PM2. 5 in Thailand | |
| Lian et al. | Sensitivity to the sources of uncertainties in the modeling of atmospheric CO 2 concentration within and in the vicinity of Paris | |
| CN112052627A (en) | Method, device, medium and equipment for estimating near-surface ozone space distribution | |
| CN114330146B (en) | Satellite gas data completion method and system | |
| CN115310550B (en) | Atmospheric carbon dioxide dry air column concentration calculation method and system | |
| CN114974453A (en) | High-coverage reconstruction method for concentration of atmospheric carbon dioxide column | |
| CN114898823A (en) | High-spatial-temporal-resolution remote sensing near-surface NO 2 Concentration estimation method and system | |
| CN116223395A (en) | Near-surface trace gas concentration inversion model and inversion method | |
| CN114463616B (en) | Multi-source satellite precipitation fusion method based on Stacking and EMOS-CSG | |
| Song et al. | Atmospheric correction of absorbing aerosols for satellite ocean color remote sensing over coastal waters | |
| CN117219183A (en) | High coverage near ground NO in cloudy rain areas 2 Concentration estimation method and system | |
| CN114357885B (en) | Photosynthetic effective radiation scattering proportion prediction method fusing multisource data | |
| CN115950832A (en) | Method for inverting near-surface nitrogen dioxide concentration based on satellite data | |
| Kustiyo et al. | Annual Forest Monitoring as part of Indonesia's National Carbon Accounting System | |
| CN115600142A (en) | Gale fusion integrated forecasting method based on different methods | |
| Running et al. | Land ecosystems and hydrology | |
| Zhang et al. | Comparisons of OCO-2 satellite derived XCO2 with in situ and modeled data over global ocean | |
| Mzé et al. | Climatology and comparison of ozone from ENVISAT/GOMOS and SHADOZ/balloon-sonde observations in the southern tropics | |
| Chazette et al. | Temporal consistency of lidar observables during aerosol transport events in the framework of the ChArMEx/ADRIMED campaign at Menorca Island in June 2013. | |
| Li et al. | A high-precision retrieval method for methane vertical profiles based on dual-band spectral data from the GOSAT satellite | |
| Goryaev et al. | Forecasting steppe fires using remote sensing data of time series | |
| Nghiem et al. | Application of GIS and remote sensing for predicting land-use change in the French Jura Mountains with the LCM model: the impact of variables on the disturbance model |
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 |