CN115310550A - Method and system for calculating concentration of atmospheric carbon dioxide dry air column - Google Patents
Method and system for calculating concentration of atmospheric carbon dioxide dry air column Download PDFInfo
- Publication number
- CN115310550A CN115310550A CN202210980540.5A CN202210980540A CN115310550A CN 115310550 A CN115310550 A CN 115310550A CN 202210980540 A CN202210980540 A CN 202210980540A CN 115310550 A CN115310550 A CN 115310550A
- Authority
- CN
- China
- Prior art keywords
- data
- xco
- covariate
- environmental
- data set
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention provides a method and a system for calculating the concentration of an atmospheric carbon dioxide dry air column, and relates to atmospheric carbon dioxide (CO) 2 ) The technical field of monitoring. The method comprises the following specific steps of collecting XCO of three remote sensing monitors in a research area 2 Preprocessing the data set and the environmental covariate data, such as gridding, space-time matching and the like; using environmental covariates, for the three XCOs 2 Fusing the data sets to obtain XCO 2 Fusing data; to XCO 2 Fusing data as a dependent variable and an environment covariate as an independent variable, and establishing a machine learning model based on an XGboost algorithm; inputting environmental covariate data into the XGboost model, and calculating to obtain XCO 2 The full domain spatio-temporal distribution of (a) reconstructs the data set. XCO integrating three remote sensing monitoring 2 Data set and reconstruction of XCO using machine learning models 2 Provides support for carbon computation of' double carbon actions。
Description
Technical Field
The invention relates to the concentration of atmospheric carbon dioxide in a column of dry air (XCO) 2 ) The technical field of monitoring, in particular to a method and a system for calculating the concentration of an atmospheric carbon dioxide dry air column.
Background
Remote sensing monitoring by using sensor carried on satellite or space station to obtain XCO 2 Important means of space-time distribution include satellite orbital carbon observation number 2 (OCO-2), greenhouse Gas Observation Satellite (GOSAT), and sensor orbital carbon observation number 3 (OCO-3) mounted on an international space station. The sensors for both OCO-2 and OCO-3 are almost identical, and each of them is equipped with three high-resolution spectrometers to measure the spectrum of the reflected sunlight around 0.76,1.61 and 2.06 micrometers, respectively. GOSAT carries with it a spectrometer for measuring the spectrum of reflected solar light at 0.76,1.61 and 2.06 microns, but also the spectrum of reflected solar light in the 5.56-14.3 micron band.
XCO for satellite monitoring 2 It is relatively sparse in space, and the missing part can be filled up by using a model simulation method. Current reconstructed full-face XCO 2 The method comprises the simulation of a Carbon Tracker model, and CO monitoring by using the ground, an airship, a satellite and the like 2 Concentration, versus atmospheric CO estimated from bottom to top 2 The concentration is corrected. However, due to computer power constraints, the resulting XCO is simulated 2 Data resolution is low, typically only 3 ° × 2 ° on a global scale. At the same time, the method relies on carbon emissions inventory,however, the statistics, collection and correction of emissions inventory data requires a long time, resulting in current XCO 2 There is some lag in the computation of the spatio-temporal distribution of the model simulation.
In recent years, there have been studies using statistical methods in combination with satellite monitoring XCO 2 Data reconstruction XCO 2 Space-time distribution, but due to XCO 2 The satellite monitoring data are relatively sparsely distributed in space, and XCO is obtained by using a Krigin interpolation method 2 Is relatively low in accuracy. According to previous researches, machine learning reconstructed atmospheric pollutant space-time distribution is higher in accuracy compared with a kriging interpolation method. And reconstructing the comprehensive domain space-time distribution of the atmospheric pollutants through machine learning modeling by utilizing the relevance between the atmospheric pollutants and environmental covariates such as weather, altitude, land utilization types and the like. Meanwhile, the machine learning method is often used for fusion application of homologous data, and limitation of a single data source can be well made up.
The invention applies the machine learning method to a plurality of remote sensing monitoring XCO 2 Fusion of datasets and reconstruction of XCO 2 Comprehensive domain space-time distribution of overcoming XCO 2 Monitoring has the problem of large amount of missing data.
Disclosure of Invention
The invention aims to provide a method and a system for calculating the concentration of an atmospheric carbon dioxide dry air column, which are used for overcoming XCO in the prior art 2 Monitoring has the problem of large amount of missing data.
In a first aspect, an embodiment of the present application provides a method for calculating a concentration of an atmospheric carbon dioxide dry air column, including the following steps:
XCO for collecting three remote sensing monitors in research area 2 The method comprises the steps of collecting data sets and environment covariate data, and preprocessing the data sets;
XCO for three remote sensing monitoring 2 Fusing the data sets to obtain XCO 2 Fusing data;
using XCO 2 Fusing data and environmental covariate data, and training to obtain an XGboost model;
inputting environmental covariate data to XGIn the Boost model, XCO is obtained through calculation 2 The full domain spatio-temporal distribution of (a) reconstructs the data set.
In the implementation process, XCO monitored by three remote sensing in a research area is collected 2 Preprocessing the data set and the environmental covariate data, such as gridding, space-time matching and the like; XCO for three remote sensing monitoring 2 Fusing the data sets to obtain XCO 2 Fusing data; using XCO 2 Fusing data and environment covariate data, and training to obtain an XGboost model; inputting environmental covariate data into the XGboost model, and calculating to obtain XCO 2 The full domain spatio-temporal distribution of (c) reconstructs the data set. XCO for monitoring three remote senses 2 Data fusion while utilizing XCO 2 The relevance between the environmental covariates such as weather, altitude, land utilization type, road density, vegetation normalization index and the like is calculated through machine learning modeling to obtain XCO 2 The full domain space-time distribution reconstructs the data set, overcomes XCO 2 The problem of monitoring the existence of a large amount of missing data.
Based on the first aspect, in some embodiments of the invention, XCO for three telemetric monitoring 2 Performing data fusion on the data set to obtain XCO 2 The steps of fusing data are as follows:
inputting:
XCO of OCO-2 2 Monitoring data a = { a = 1 ，...，a j ，...，a J }；
XCO of OCO-3 2 Monitoring data B = { B = 1 ，...，b j ，...，b J }；
XCO of GOSAT 2 Monitoring data C = { C 1 ，…，c j ，…，c J }；
Environmental covariances volume data set D = { D = 1 ，...，d j ，...，d J }；
Note: wherein d is j Representing the set of values of all environment covariates at j, not the jth environment covariate. d j And a j 、b j And c j Corresponding in space-time, i.e. three sensors are in the same positionAnd (5) observing values of the same grid. Due to the different degree of deletion of the OCO-2, OCO-3 and GOSAT data, a j 、b j And c j Missing values may exist but not at the same time.
And (3) outputting: fused data set E = { E = { E = } 1 ，...，e j ，...，e J }；
The method comprises the following steps:
(1) and the fusion A and the fusion B are O:
wherein O = { O = 1 ，...，o j ，...，o J }，o j ＝f 1 (a j ，b j ) Wherein a is j ，b j At least one is non-empty;
f 1 is the fusion function:
(2) linear transformation of GOSAT dataset C:
S＝{j|O j is not empty and C j Non-null };
M＝{c s |s∈S}，N＝{o s |s∈S}；
establishing a linear model f 3 ：N←M；
Based on f 3 Transformation of c j ：
J from 1 to J:
when c is going to j Is not empty and
c′ j ＝f 3 (c j )；
the converted data set was C '= { C' 1 ，...，c′ j ，...，c′ J }；
(3) Obtaining the final XCO by taking the union of the data set O and the data set C 2 The data set E is fused.
Based on the first aspect, XCO is used in some embodiments of the invention 2 The XGboost model is established by fusing data and environmental covariate data as follows:
to XCO 2 And (5) taking the fusion data as a dependent variable and taking the environmental covariate as an independent variable, and training to obtain the XGboost model.
Based on the first aspect, in some embodiments of the present invention, the preprocessing of the environmental covariate data of the research area comprises the following steps:
carrying out space division on a research area to obtain a space grid with 1km resolution;
assigning the environmental covariate data into a predefined grid by adopting methods such as spatial resampling and the like;
in a second aspect, an embodiment of the present application provides an atmospheric carbon dioxide dry air column concentration calculation system, including:
a data acquisition module for collecting XCO of three remote sensing monitors in the research area 2 A dataset and environmental covariate data;
data preprocessing module for XCO of three remote sensing monitoring in research area 2 Preprocessing the data set and the environmental covariate data such as gridding, space-time matching and the like to obtain a preprocessed data set;
data fusion module for XCO of three remote sensing monitoring 2 Carrying out data fusion on the data set to obtain XCO 2 Fusing the data sets;
an XGboost model establishing module used for establishing a model based on XCO 2 Training fused data and environmental covariate data to obtain an XGboost model;
a concentration calculation module used for inputting environmental covariate data into the XGboost model and obtaining XCO through calculation 2 The full domain spatio-temporal distribution of (a) reconstructs the data set.
In the implementation process, XCO monitored by three remote sensing in a research area is collected 2 Preprocessing the data set and the environmental covariate data, such as gridding, space-time matching and the like; XCO for three remote sensing monitoring 2 Fusing the data sets to obtain XCO 2 Fusing data; using XCO 2 Fusing data and environment covariate data, and training to obtain XGboost modelMolding; inputting environmental covariate data into the XGboost model, and calculating to obtain XCO 2 The full domain spatio-temporal distribution of (a) reconstructs the data set. XCO for three remote sensing monitoring 2 Data fusion while utilizing XCO 2 The correlation between the environmental covariates such as weather, altitude, land utilization type, road density, vegetation normalization index and the like is calculated through machine learning modeling to obtain XCO 2 The full domain space-time distribution reconstructs the data set, overcomes XCO 2 The problem of monitoring the existence of a large amount of missing data.
The embodiment of the invention at least has the following advantages or beneficial effects:
the embodiment of the invention provides a method and a system for calculating the concentration of an atmospheric carbon dioxide dry air column, which are used for collecting XCO monitored by three remote sensing in a research area 2 Preprocessing the data set and the environmental covariate data, such as gridding, space-time matching and the like; XCO for three remote sensing monitoring 2 Carrying out data fusion on the data set to obtain XCO 2 Fusing data; using XCO 2 Fusing data and environmental covariate data, and training to obtain an XGboost model; inputting the environment covariate number set into the XGboost model, and calculating to obtain XCO 2 The full domain spatio-temporal distribution of (a) reconstructs the data set. XCO for monitoring three remote senses 2 Data set fusion while utilizing XCO 2 The relevance between the environmental covariates such as weather, altitude, land utilization type, road density, vegetation normalization index and the like is calculated through machine learning modeling to obtain XCO 2 The full domain space-time distribution reconstructs the data set, overcomes XCO 2 The problem of monitoring the existence of a large amount of missing data.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
FIG. 1 is a flow chart of a method for calculating the concentration of an atmospheric column of carbon dioxide dry air according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a data fusion process provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of the spatial and temporal composition distribution of the respective remote sensing data and the fused data provided by the embodiment of the present invention;
fig. 4 is a block diagram of a system for calculating the concentration of the atmospheric carbon dioxide dry air column according to an embodiment of the present invention.
Icon: 110-a data acquisition module; 120-a data pre-processing module; 130-a data fusion module; a 140-XGboost model building module; 150-concentration calculation module.
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. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, as presented in the figures, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
Examples
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments and features of the embodiments described below can be combined with one another without conflict.
Referring to fig. 1-2, fig. 1 is a flowchart of a method for calculating a concentration of an atmospheric carbon dioxide dry air column according to an embodiment of the present invention, and fig. 2 is a schematic diagram of a data fusion process according to an embodiment of the present invention. The method for calculating the concentration of the atmospheric carbon dioxide dry air column comprises the following steps:
step S110: collecting remote sensing monitoring XCO in research area 2 Data and environmental covariate data. XCO as described above 2 XCO with data comprising three remote sensing monitors 2 Data set comprising XCO from satellite orbital carbon observation number 2 (OCO-2) 2 Data, XCO from greenhouse Gas Observation Satellites (GOSAT) 2 Data, and XCO from sensor orbit carbon observation number 3 (OCO-3) carried on International space station 2 And (4) data. The data sets include weather, population density, planet boundary layer height, land use type, normalized vegetation index, elevation, road information, and the like. The weather data come from a European middle-term weather forecast center, the land utilization type data come from a European space agency climate change research institute, the altitude data come from a space shuttle radar terrain task, and the population density data come from gridded world population.
Environmental covariate data for the study area is pre-processed. The preprocessing is to process environmental covariate data into a predefined 1km grid by gridding, space-time matching and other methods for training and calculating a machine learning model, and the data set usually includes tens to hundreds of variables. The method specifically comprises the following steps:
firstly, a research area is spatially divided to obtain a spatial grid with a resolution of 1 km.
And then, evaluating the environmental covariate data to a predefined 1km grid by adopting gridding, space-time matching and other methods to obtain a preprocessed environmental covariate data set.
Step S120: XCO for three remote sensing monitoring 2 Performing data fusion on the data set to obtain XCO 2 Fusing data, comprising the following steps:
inputting:
XCO of OCO-2 2 Monitoring data a = { a = 1 ，...，a j ，...，a J }；
XCO of OCO-3 2 Monitoring data B = { B = { B = } 1 ，...，b j ，...，b J }；
XCO of GOSAT 2 Monitoring data C = { C 1 ，…，c j ，…，c J }；
Environmental covariate data set D = { D = { (D) } 1 ，...，d j ，...，d J }；
Note: wherein d is j Representing the set of values of all environment covariates at j, not the jth environment covariate. d j And a j 、b j And c j The three sensors are corresponding to each other in time and space, namely, the observed values of the three sensors on the same day and the same grid. Due to the different degree of deletion of the OCO-2, OCO-3 and GOSAT data, a j 、b j And c j Missing values may exist but not at the same time.
And (3) outputting: fused data set E = { E = { E = } 1 ，...，e j ，...，e J }；
The method comprises the following steps:
(1) and the fusion A and the fusion B are O:
wherein O = { O = 1 ，...，o j ，...，o J }，o j ＝f 1 (a j ，b j ) Wherein a is j ，b j At least one is non-empty;
f 1 is a fusion function:
(2) linear transformation of GOSAT dataset C:
S＝{j|O j is not empty and C j Non-null };
M＝{c s |s∈S}，N＝{o s |s∈S}；
establishing a Linear model f 3 ：N←M；
Based on f 3 Transformation of c j ：
J from 1 to J:
when c is j Is not empty and
c′ j ＝f 3 (c j )；
the converted data set was C '= { C' 1 ，...，c′ j ，...，c′ J }；
(3) Obtaining the final XCO by taking the union of the data set O and the data set C 2 The data set E is fused.
Step S130: using XCO 2 Fusing data as a dependent variable and an environmental covariate as an independent variable, and training to obtain a machine learning model based on the XGboost algorithm;
step S140: inputting environmental covariate data into the XGboost model, and calculating to obtain XCO 2 The full domain spatio-temporal distribution of (a) reconstructs the data set.
In the implementation process, XCO monitored by three remote sensing in a research area is collected 2 Preprocessing the data set and the environmental covariate data, such as gridding, space-time matching and the like; XCO for three remote sensing monitoring 2 Fusing the data sets to obtain XCO 2 Fusing data; using XCO 2 Fusing data and environment covariate data, and training to obtain an XGboost model; inputting environmental covariate data into the XGboost model, and calculating to obtain XCO 2 The full domain spatio-temporal distribution of (c) reconstructs the data set. XCO for three remote sensing monitoring 2 Data set fusion while utilizing XCO 2 The relevance between the environmental covariates such as weather, altitude, land utilization type, road density, vegetation normalization index and the like is calculated through machine learning modeling to obtain XCO 2 The full domain spatio-temporal distribution of (c) reconstructs the data set.
Referring to fig. 3, fig. 3 is a schematic diagram of a data fusion process provided by an embodiment of the present invention, in which the horizontal axis represents space and the vertical axis represents time. In the diagram, C = G + S denotes XCO for GOSAT monitoring 2 A data set with data throughout the time interval P; o = T + S denotes XCO for OCO (OCO-2 and OCO-3) monitoring 2 Data set, only in time interval P 1 Data is present. At P 1 Interval, GOSAT monitored XCO 2 And OCO monitored XCO 2 There is a distribution of data points. Due to the orbits of the satellite and the space station, adverse meteorological conditions and the like, the satellite data of the daily scale is missing spatially, and XCO monitored by OCO 2 Covering only O space, while XCO monitored by GOSAT 2 In the P period, only the C space-time interval is covered, and the S space-time interval is a spatially overlapped portion of the C space-time interval and the C space-time interval. And performing linear fitting on the GOSAT monitoring value and the OCO monitoring value in the S space-time interval, and establishing a linear model by taking the GOSAT monitoring value as an independent variable and the OCO monitoring value as a dependent variable. The linear model is utilized to convert the GOSAT monitoring value of the G part into the OCO monitoring value, so that the OCO monitoring value approximately covers the G space interval, the time interval covers the whole P time period, and a plurality of XCOs are realized 2 Fusion of the data is monitored.
Based on the same inventive concept, the invention further provides a system for calculating the concentration of the dry air column of atmospheric carbon dioxide, please refer to fig. 4, and fig. 4 is a block diagram of the structure of the system for calculating the concentration of the dry air column of atmospheric carbon dioxide according to the embodiment of the invention. The atmospheric carbon dioxide dry air column concentration calculation system comprises:
a data acquisition module 110 for collecting XCO of three remote sensing monitors in the research area 2 A dataset and environmental covariate data;
a data pre-processing module 120 for comparing XCO in the research area 2 Preprocessing the data and environment covariate data to obtain preprocessed XCO 2 A dataset and an environmental covariate dataset;
an XGboost model building module 140 for XCO-based 2 Fusing data and environment covariate data to establish an XGboost model;
a concentration calculation module 150, configured to input environment covariate data into the XGBoost model, and calculate to obtain XCO 2 The full domain spatio-temporal distribution of (a) reconstructs the data set.
In the implementation process, XCO monitored by three remote sensing in a research area is collected 2 Preprocessing the data set and the environmental covariate data, such as gridding, space-time matching and the like; XCO for three remote sensing monitoring 2 Fusing the data sets to obtain XCO 2 Number of fusionAccordingly; using XCO 2 Fusing data and environmental covariate data, and training to obtain an XGboost model; inputting environmental covariate data into the XGboost model, and calculating to obtain XCO 2 The full domain spatio-temporal distribution of (c) reconstructs the data set. XCO for monitoring three remote senses 2 Data fusion while utilizing XCO 2 The relevance between the environmental covariates such as weather, altitude, land utilization type, road density, vegetation normalization index and the like is calculated through machine learning modeling to obtain XCO 2 The full domain spatio-temporal distribution of (c) reconstructs the data set.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (5)
1. Concentration of atmospheric carbon dioxide in dry air column (XCO) 2 ) The spatial-temporal distribution reconstruction method is characterized by comprising the following steps of:
XCO for collecting three remote sensing monitors in research area 2 A data set (comprising OCO-2, OCO-3 and GOSAT) and environment covariate data in the region, and preprocessing the data set;
XCO for three remote sensing monitoring 2 Fusing the data sets to obtain XCO 2 Fusing the data sets;
using XCO 2 Fusing data as a dependent variable and an environmental covariate as an independent variable, and training to obtain a machine learning model based on the XGboost algorithm;
inputting environmental covariate data into the XGboost model, and calculating to obtain XCO 2 The full domain spatio-temporal distribution of (c) reconstructs the data set.
2. The method of calculating the concentration of an atmospheric column of carbon dioxide in dry air according to claim 1, wherein the XCO over three telemetric monitoring 2 The steps of fusing the data sets are as follows:
inputting:
XCO of OCO-2 2 Monitoring data a = { a = 1 ，...，a j ，...，a J }；
XCO of OCO-3 2 Monitoring data B = { B = { B = } 1 ，...，b j ，...，b J }；
XCO of GOSAT 2 Monitoring data C = { C 1 ，...，c j ，...，c J }；
Environmental covariances volume data set D = { D = { (D) } 1 ，...，d j ，...，d J }；
Note: wherein d is j Representing the set of values of all environment covariates at j, not the jth environment covariate. d j And a j 、b j And c j The three sensors are corresponding to each other in space and time, namely the observed values of the three sensors on the same day and the same grid. Since there are different degrees of deletions in OCO-2, OCO-3 and GOSAT data, a j 、b j And c j Missing values may exist but not at the same time.
And (3) outputting: fused data set E = { E = { E = } 1 ，...，e j ，...，e J }；
The method comprises the following steps:
(1) and the fusion A and the fusion B are O:
wherein O = { O = 1 ，...，o j ，...，o J }，o j ＝f 1 (a j ，b j ) Wherein a is j ，b j At least one is non-empty;
f 1 is the fusion function:
(2) linear transformation of GOSAT dataset C:
S＝{j|O j is not empty and C j Non-null };
M＝{c s |s∈S}，N＝{o s |s∈S}；
establishing a Linear model f 3 ：N←M；
Based on f 3 Transformation of c j ：
J is from 1 to J:
when c is j Is not empty and
c′ j ＝f 3 (c j )
the converted data set was C '= { C' 1 ，...，c′ j ，...，c′ J }
(3) The union of the data set O and the data set C' is taken to obtain the final XCO 2 The data set E is fused.
3. The method of calculating the concentration of an atmospheric column of carbon dioxide dry air as claimed in claim 2, wherein said using XCO 2 The XGboost model is established by fusing data and environmental covariates as follows:
to XCO 2 And (5) taking the fused data as a dependent variable and taking the environmental covariate as an independent variable, and training to obtain the XGboost model.
4. The method of calculating the concentration of an atmospheric column of carbon dioxide dry air according to claim 1, comprising preprocessing environmental covariate data in the study area, comprising the steps of:
carrying out space division on a research area to obtain a space grid with 1km resolution;
and assigning the environmental covariate data into a predefined grid by adopting methods such as spatial resampling and the like.
5. An atmospheric carbon dioxide dry air column concentration calculation system, comprising:
a data acquisition module for collecting XCO monitored by three remote sensing in the research area 2 A data set and environmental covariate data;
data preprocessing module, XCO for three remote sensing monitoring in research area 2 Preprocessing the data set and the environmental covariate data such as gridding, space-time matching and the like to obtain a preprocessed data set;
data fusion module for XCO of three remote sensing monitoring 2 Carrying out data fusion on the data set to obtain XCO 2 Fusing the data sets;
XGboost model establishing module for XCO-based 2 Training fused data and environmental covariate data to obtain an XGboost model;
a concentration calculation module used for inputting environmental covariate data into the XGboost model and calculating to obtain XCO 2 The full domain spatio-temporal distribution of (a) reconstructs the data set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210980540.5A CN115310550B (en) | 2022-08-16 | 2022-08-16 | Atmospheric carbon dioxide dry air column concentration calculation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210980540.5A CN115310550B (en) | 2022-08-16 | 2022-08-16 | Atmospheric carbon dioxide dry air column concentration calculation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115310550A true CN115310550A (en) | 2022-11-08 |
| CN115310550B CN115310550B (en) | 2023-07-14 |
Family
ID=83862862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210980540.5A Active CN115310550B (en) | 2022-08-16 | 2022-08-16 | Atmospheric carbon dioxide dry air column concentration calculation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115310550B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116882261A (en) * | 2023-05-30 | 2023-10-13 | 中国矿业大学 | Atmospheric XCO integrating land surface environment variables 2 Concentration refinement inversion method |
| CN117556953A (en) * | 2023-11-21 | 2024-02-13 | 中国气象局沈阳大气环境研究所 | Automatic processing and predicting system based on satellite remote sensing inversion data |
| CN117574155A (en) * | 2023-11-29 | 2024-02-20 | 海南省气象科学研究所 | Prediction method for near-ground atmospheric carbon dioxide concentration in sea area based on satellite remote sensing |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2827200A1 (en) * | 2001-07-12 | 2003-01-17 | Usinor | Metal strip continuous coating procedure uses molten polymer applied and spread evenly to moving strip |
| US20130179078A1 (en) * | 2009-11-26 | 2013-07-11 | Tanguy Griffon | Method for measuring weekly and annual emissions of a greenhouse gas over a given surface area |
| AU2015201877A1 (en) * | 2006-05-31 | 2015-05-14 | TRX Systems, Inc, | Method and system for locating and monitoring first responders |
| US20180156766A1 (en) * | 2016-12-06 | 2018-06-07 | Ning Zeng | Networked Environmental Monitoring System and Method |
| CN111893237A (en) * | 2020-07-08 | 2020-11-06 | 北京科技大学 | Method for predicting carbon content and temperature of molten pool of converter steelmaking in whole process in real time |
| CN112884079A (en) * | 2021-03-30 | 2021-06-01 | 河南大学 | Method for estimating near-surface nitrogen dioxide concentration based on Stacking integrated model |
| 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 |
| CN113297527A (en) * | 2021-06-09 | 2021-08-24 | 四川大学 | PM based on multisource city big data2.5Overall domain space-time calculation inference method |
| CN113435511A (en) * | 2021-06-28 | 2021-09-24 | 中国科学院地理科学与资源研究所 | XCO based on HASM2Data fusion method and system |
| CN114861882A (en) * | 2022-05-07 | 2022-08-05 | 国网四川省电力公司电力科学研究院 | CO (carbon monoxide) 2 Space-time distribution reconstruction method and system |
-
2022
- 2022-08-16 CN CN202210980540.5A patent/CN115310550B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2827200A1 (en) * | 2001-07-12 | 2003-01-17 | Usinor | Metal strip continuous coating procedure uses molten polymer applied and spread evenly to moving strip |
| AU2015201877A1 (en) * | 2006-05-31 | 2015-05-14 | TRX Systems, Inc, | Method and system for locating and monitoring first responders |
| US20130179078A1 (en) * | 2009-11-26 | 2013-07-11 | Tanguy Griffon | Method for measuring weekly and annual emissions of a greenhouse gas over a given surface area |
| US20180156766A1 (en) * | 2016-12-06 | 2018-06-07 | Ning Zeng | Networked Environmental Monitoring System and Method |
| CN111893237A (en) * | 2020-07-08 | 2020-11-06 | 北京科技大学 | Method for predicting carbon content and temperature of molten pool of converter steelmaking in whole process in real time |
| CN112884079A (en) * | 2021-03-30 | 2021-06-01 | 河南大学 | Method for estimating near-surface nitrogen dioxide concentration based on Stacking integrated model |
| CN113297527A (en) * | 2021-06-09 | 2021-08-24 | 四川大学 | PM based on multisource city big data2.5Overall domain space-time calculation inference method |
| 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 |
| CN113435511A (en) * | 2021-06-28 | 2021-09-24 | 中国科学院地理科学与资源研究所 | XCO based on HASM2Data fusion method and system |
| CN114861882A (en) * | 2022-05-07 | 2022-08-05 | 国网四川省电力公司电力科学研究院 | CO (carbon monoxide) 2 Space-time distribution reconstruction method and system |
Non-Patent Citations (2)
| Title |
|---|
| HEATHER D. COUTURE 等: "Towards Tracking the Emissions of Every Power Plant on the Planet", 《NEURIPS》, pages 1 - 9 * |
| 莫露 等: "中国XCO2时空分布与影响因素分析", 《中国环境科学》, vol. 41, no. 6, pages 2562 - 2570 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116882261A (en) * | 2023-05-30 | 2023-10-13 | 中国矿业大学 | Atmospheric XCO integrating land surface environment variables 2 Concentration refinement inversion method |
| CN116882261B (en) * | 2023-05-30 | 2024-08-09 | 中国矿业大学 | Atmospheric XCO integrating land surface environment variables2Concentration refinement inversion method |
| CN117556953A (en) * | 2023-11-21 | 2024-02-13 | 中国气象局沈阳大气环境研究所 | Automatic processing and predicting system based on satellite remote sensing inversion data |
| CN117556953B (en) * | 2023-11-21 | 2024-08-06 | 中国气象局沈阳大气环境研究所 | Automatic processing and predicting system based on satellite remote sensing inversion data |
| CN117574155A (en) * | 2023-11-29 | 2024-02-20 | 海南省气象科学研究所 | Prediction method for near-ground atmospheric carbon dioxide concentration in sea area based on satellite remote sensing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115310550B (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113297527B (en) | PM based on multisource city big data 2.5 Overall domain space-time calculation inference method | |
| CN115310550B (en) | Atmospheric carbon dioxide dry air column concentration calculation method and system | |
| Michel et al. | The WACMOS-ET project–Part 1: Tower-scale evaluation of four remote-sensing-based evapotranspiration algorithms | |
| CN113297528B (en) | NO based on multi-source big data2High-resolution space-time distribution calculation method | |
| Yang et al. | Geographical and temporal encoding for improving the estimation of PM2. 5 concentrations in China using end-to-end gradient boosting | |
| CN112884079A (en) | Method for estimating near-surface nitrogen dioxide concentration based on Stacking integrated model | |
| Kong et al. | Matching high resolution satellite data and flux tower footprints improves their agreement in photosynthesis estimates | |
| Cui et al. | Generation of spatio-temporally continuous evapotranspiration and its components by coupling a two-source energy balance model and a deep neural network over the Heihe River Basin | |
| Yang et al. | Mapping PM2. 5 concentration at a sub-km level resolution: A dual-scale retrieval approach | |
| Chen et al. | Obtaining vertical distribution of PM2. 5 from CALIOP data and machine learning algorithms | |
| Thornton et al. | Daymet: monthly climate summaries on a 1-km grid for North America, Version 3. ORNL DAAC, Oak Ridge, Tennessee, USA | |
| Wei et al. | Spatial–temporal variations of NDVI and its response to climate in China from 2001 to 2020 | |
| CN108491667B (en) | PM2.5 remote sensing monitoring inversion method based on Himapari-8 AOD | |
| Jin et al. | Global validation and hybrid calibration of CAMS and MERRA-2 PM2. 5 reanalysis products based on OpenAQ platform | |
| CN111652404A (en) | All-weather earth surface temperature inversion method and system | |
| Thornton et al. | Daymet: Annual Climate Summaries on a 1-km Grid for North America, Version 4 R1. ORNL DAAC, Oak Ridge, Tennessee, USA | |
| Bai et al. | Multiscale and multisource data fusion for full-coverage PM2. 5 concentration mapping: Can spatial pattern recognition come with modeling accuracy? | |
| Chen et al. | High spatiotemporal resolution estimation of AOD from Himawari-8 using an ensemble machine learning gap-filling method | |
| CN115239175B (en) | Rapid estimation method and system for total production value of land ecological system | |
| Zhang et al. | Estimation of PM 2.5 mass concentrations in Beijing–Tianjin–Hebei region based on geographically weighted regression and spatial downscaling method | |
| Cawse-Nicholson et al. | Evaluation of a CONUS-wide ECOSTRESS DisALEXI evapotranspiration product | |
| Flückiger et al. | Modelling daily air temperature at a fine spatial resolution dealing with challenging meteorological phenomena and topography in Switzerland | |
| Wei et al. | Extending the EOS long-term PM 2.5 data records since 2013 in China: Application to the VIIRS deep blue aerosol products | |
| Qin et al. | Reconstruction of 60-year (1961–2020) surface air temperature on the Tibetan Plateau by fusing MODIS and ERA5 temperatures | |
| CN115420690A (en) | Near-surface trace gas concentration inversion model and inversion method |
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 |