CN116415110B - Method for carrying out carbon emission partition gridding based on multisource remote sensing density data - Google Patents
Method for carrying out carbon emission partition gridding based on multisource remote sensing density data Download PDFInfo
- Publication number
- CN116415110B CN116415110B CN202310651468.6A CN202310651468A CN116415110B CN 116415110 B CN116415110 B CN 116415110B CN 202310651468 A CN202310651468 A CN 202310651468A CN 116415110 B CN116415110 B CN 116415110B
- Authority
- CN
- China
- Prior art keywords
- data
- provincial
- carbon emission
- remote sensing
- source
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 176
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 176
- 238000005192 partition Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 48
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 36
- 238000012549 training Methods 0.000 claims description 23
- 238000011160 research Methods 0.000 claims description 22
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 18
- 239000001569 carbon dioxide Substances 0.000 claims description 18
- 238000012360 testing method Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000000638 solvent extraction Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 238000012952 Resampling Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000002803 fossil fuel Substances 0.000 description 2
- 238000010792 warming Methods 0.000 description 2
- DFPOZTRSOAQFIK-UHFFFAOYSA-N S,S-dimethyl-beta-propiothetin Chemical compound C[S+](C)CCC([O-])=O DFPOZTRSOAQFIK-UHFFFAOYSA-N 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
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
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0475—Generative networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/094—Adversarial learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Optimization (AREA)
- General Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Strategic Management (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Analysis (AREA)
- Economics (AREA)
- Computational Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Evolutionary Biology (AREA)
- Educational Administration (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Algebra (AREA)
- Tourism & Hospitality (AREA)
Abstract
The application discloses a method for carrying out carbon emission partition gridding based on multi-source remote sensing density data. The application considers the difference of the relation between the total carbon emission and the multi-source data caused by inconsistent areas of each province, uses the multi-source density data with higher rationality, combines the multi-source density data with the carbon emission level partition factor to obtain the carbon emission partition gridding model, and can provide help for generating grid-level carbon emission data from regional scale to more local scale.
Description
Technical Field
The application relates to the technical field of carbon dioxide gas emission space management, in particular to a method for carrying out carbon emission partition gridding based on multi-source remote sensing density data.
Background
Carbon emissions from human activity are a major cause of global warming, with fossil fuels being the largest source of carbon emissions and becoming the primary contributor to climate warming. Therefore, accurate assessment of carbon dioxide emissions from chinese fossil fuels is of paramount importance. At present, the acquisition methods of the carbon emission data of the small area are mainly divided into two types. The method is mainly based on a mode of manually acquiring carbon emission data, is time-consuming, labor-consuming and time-lagging, and has the problems of serious inconsistency and the like due to different statistical calibers, calculation modes and statistical errors. The other is to calculate the artificial carbon emission in a small area by a spatialization method according to the energy consumption data issued by national and provincial departments. Methods commonly used for carbon emission spatialization include parametric methods and non-parametric methods. The parametric model is to assign the total amount of carbon emission data to each grid cell assuming a simple linear relationship between the total amount of area and the grid of cells. However, the traditional multiple regression analysis method cannot describe the complex nonlinear relation between carbon emission and remote sensing variables due to simple calculation, and the obtained model is only applicable to specific areas. The non-parametric model is used for carrying out meshing on the carbon emission by utilizing a machine learning or deep learning method to mine complex nonlinear relations between the carbon emission and various remote sensing characteristics.
The existing research mainly starts from multi-source total data such as night light data, population and the like, introduces a deep learning method, digs the relation between the data and the total carbon emission, and uses the data for grid generation of domestic energy consumption carbon emission statistical data. These methods have a technical problem of large error in performing the carbon discharge gridding.
Disclosure of Invention
The application provides a method for carrying out carbon emission partition gridding based on multisource remote sensing density data, which is used for solving or at least partially solving the technical problem of larger error in the prior art.
In order to solve the technical problems, the application discloses a method for carrying out carbon emission partition gridding based on multi-source remote sensing density data, which comprises the following steps:
s1: acquiring provincial carbon emission statistical data and multisource remote sensing data in a research area, and preprocessing the acquired multisource remote sensing data;
s2: generating provincial multi-source data according to the preprocessed multi-source remote sensing data;
s3: performing density conversion on the provincial multi-source data and the provincial carbon emission statistical data respectively to generate provincial multi-source density data and provincial carbon emission density data;
s4: performing carbon emission grade division on the provincial carbon emission statistical data, and partitioning a research area according to the carbon emission grade;
s5: respectively constructing corresponding generated countermeasure network models according to the subareas in the step S4, serving as a carbon emission subarea gridding model corresponding to each subarea, and training the generated countermeasure network models by using the generated provincial multi-source density data and the provincial carbon emission density data;
s6: and inputting grid-level multi-source data of different partitions into a trained carbon emission partition gridding model based on a generated countermeasure network S5 to obtain a national grid-level 1km multiplied by 1km carbon emission spatial distribution map.
In one embodiment, S1 pre-processing the acquired multi-source remote sensing data includes: and projecting, cutting and grid alignment are carried out on the acquired multi-source remote sensing data.
In one embodiment, the multi-source telemetry data includes watertight surface data, air temperature data, night light data, GDP data, and demographic data, and step S2 includes:
respectively carrying out provincial statistics on the preprocessed impervious surface data, night light data, GDP data and population data to generate provincial impervious total area data, provincial night light total amount data, provincial GDP total amount data and provincial population total amount data;
carrying out provincial average processing on the preprocessed air temperature data to generate provincial air temperature data;
the provincial waterproof total area data, the provincial night light total amount data, the provincial GDP total amount data, the provincial population total amount data and the provincial air temperature data form provincial multisource data.
In one embodiment, step S3 includes:
dividing the provincial waterproof total area data, the provincial night light total amount data, the provincial GDP total amount data, the provincial population total amount data and the provincial carbon emission statistical data by each provincial area to generate provincial waterproof density data, provincial luminous density data, provincial GDP density data, provincial population density data and provincial carbon emission density data;
provincial waterproof density data, provincial luminous density data, provincial GDP density data, provincial population density data and preprocessed air temperature data form provincial multisource density data.
In one embodiment, step S4 includes:
establishing a time sequence data sequence of carbon dioxide emission data of each province, analyzing the time trend of the carbon dioxide emission quantity of each province in the target year by using Slope analysis, and calculating the following formula:
wherein n is the total number of years involved;is the serial number of the ith year; />Carbon dioxide emission amount of a certain province corresponding to the ith year;
and dividing the carbon emission levels of each province according to the average value and the standard deviation of the Slope to obtain a slow growth zone, a medium speed growth zone, a faster growth zone and a rapid growth zone.
In one embodiment, step S5 includes:
for each divided partition, constructing a corresponding generated countermeasure network model as a carbon emission partition meshing model;
dividing the generated provincial multi-source density data and provincial carbon emission density data into a training set and a testing set which correspond to the partition according to a preset proportion;
and respectively training, parameter optimization and verification on the corresponding carbon emission partition gridding model by utilizing the obtained training set and the test set to obtain a trained carbon emission partition gridding model based on the generated countermeasure network.
In one embodiment, step S6 includes:
acquiring multi-source remote sensing data in a research area and preprocessing the multi-source remote sensing data;
resampling the preprocessed multi-source remote sensing data to generate grid-level multi-source remote sensing data, wherein the spatial resolution is 1km multiplied by 1km;
and inputting resampled grid-level multisource remote sensing data in the research area into a grid model which is trained in S5 and is based on the carbon emission amount of the generated countermeasure network in a partitioned mode, and outputting a grid-level 1km multiplied by 1km carbon emission spatial distribution map of the whole country.
Compared with the prior art, the application has the following advantages and beneficial technical effects:
1. compared with modeling by commonly using the total carbon emission amount in the prior art, the method performs density conversion on the provincial multi-source data and the provincial carbon emission statistical data, and performs carbon dioxide emission meshing modeling by using the density, so that the difference of the relation between the total carbon emission amount and the multi-source data caused by inconsistent areas of each provincial is considered, the method has higher rationality, and is beneficial to improving the accuracy of carbon emission meshing.
2. Compared with the existing method for establishing only one carbon emission gridding model for a research area, the method for classifying the carbon emission grade of the application divides the provincial carbon emission statistical data into carbon emission grades, and divides the research area according to the carbon emission grades, and the adopted division method considers the difference of carbon dioxide emission influence factors caused by different regions, reflects the carbon emission distribution characteristics of the areas with different carbon emission growing trends, avoids the problem of misestimation of carbon emission caused by unified modeling, and can provide help for generating grid-grade carbon emission data from regional scale to more local scale.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is an overall flowchart of a method for performing carbon emission partition meshing based on multi-source remote sensing density data according to an embodiment of the present application.
Detailed Description
The present inventors have found through a great deal of research and practice that: in the prior art, a deep learning method is introduced mainly from multi-source total data such as night light data and population, the relation between the data and the total carbon emission is excavated, and the data is used for grid generation of domestic energy consumption carbon emission statistical data. These methods have two main problems: firstly, the inconsistent area of each province is not considered, the relation between the total carbon emission and the multisource total data can be different, and the actual carbon emission increase condition of each province can not be shown; and secondly, analysis is carried out based on the whole research area, the carbon discharge meshing error caused by the difference of different carbon discharge acceleration areas is not considered, and a deep learning model containing the spacial carbon discharge of a wide area may not be applicable to all areas. Therefore, considering different carbon emission acceleration rates of various provinces in China and different economic development levels, a deep learning method for partitioning and gridding the carbon emission based on multi-source remote sensing density data, which takes the different carbon emission acceleration rates into consideration, needs to be established, and a new technical approach is provided for obtaining the large-scale high-spatial-resolution time series carbon emission data in China.
The application provides a method for carrying out carbon emission partition gridding based on multi-source remote sensing density data, which comprises the steps of firstly combining the multi-source remote sensing density data with carbon emission grade partition, then creating a non-parameter carbon emission gridding model (generating an countermeasure network model) of the multi-source remote sensing density data considering different carbon emission acceleration, and generating a national grid level 1km multiplied by 1km carbon emission spatial distribution map by using the model. The application considers the difference of the relation between the total carbon emission and the multi-source data caused by inconsistent areas of each province, uses the multi-source density data with higher rationality, combines the multi-source density data with the carbon emission level partition factor to obtain the carbon emission partition gridding model, and can provide help for generating grid-level carbon emission data from regional scale to more local scale.
It should be noted that, in the existing method for generating a nationwide 1km carbon emission spatial distribution map by combining multi-source data, a unified and nationwide model is established, while the application performs partition modeling (each partition corresponds to a model) based on the partition factor of the carbon emission level, considers the carbon emission distribution characteristics of different carbon emission growing trends, and can avoid the problem that the model has larger simulation error in carbon emission in certain areas caused by unified modeling, thereby obtaining more accurate grid-level carbon emission data; the generation countermeasure network model adopted by the application is proved by a literature to be a model with better carbon emission spatialization effect, and compared with a random forest model, the model is greatly improved. The main ideas and steps of carbon emission partition modeling are: firstly, analyzing the time trend of the carbon dioxide emission of each province in a target year by using Slope analysis to obtain Slope values of each province (the Slope values can reflect the trend degree of increasing or reducing carbon emission); and then dividing the carbon emission grades of each province according to the average value and the standard deviation of the Slope to obtain carbon emission partitions. Finally, modeling is performed according to the carbon emission partition, for example, in the embodiment of the application, models (four models in total) are respectively built for a slow growth region, a medium speed growth region, a faster growth region and a rapid growth region. Therefore, the idea of partition modeling is designed based on the carbon emission distribution characteristics of different carbon emission growing trends, and the problem that the model has larger carbon emission simulation errors in certain areas due to unified modeling can be avoided.
The method and the device for determining the fine scale based on the energy consumption carbon emission disclosed in the prior art adopt a bottom-up carbon emission estimation method, do not involve a meshing process, and directly gather the obtained carbon emission point source data to a corresponding region. The application uses a top-down carbon emission method, and the provincial large-scale carbon emission data are distributed to the grid-level small-scale carbon emission data through gridding, so that obvious differences exist between the provincial large-scale carbon emission data and the grid-level small-scale carbon emission data.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The embodiment of the application provides a method for carrying out carbon emission partition gridding based on multi-source remote sensing density data, which comprises the following steps:
s1: acquiring provincial carbon emission statistical data and multisource remote sensing data in a research area, and preprocessing the acquired multisource remote sensing data;
s2: generating provincial multi-source data according to the preprocessed multi-source remote sensing data;
s3: performing density conversion on the provincial multi-source data and the provincial carbon emission statistical data respectively to generate provincial multi-source density data and provincial carbon emission density data;
s4: performing carbon emission grade division on the provincial carbon emission statistical data, and partitioning a research area according to the carbon emission grade;
s5: respectively constructing corresponding generated countermeasure network models according to the subareas in the step S4, serving as a carbon emission subarea gridding model corresponding to each subarea, and training the generated countermeasure network models by using the generated provincial multi-source density data and the provincial carbon emission density data;
s6: and inputting grid-level multi-source data of different partitions into a trained carbon emission partition gridding model based on a generated countermeasure network S5 to obtain a national grid-level 1km multiplied by 1km carbon emission spatial distribution map.
In general, the method for carrying out carbon emission partition gridding based on multi-source remote sensing density data provided by the application divides a research area through carbon emission classification and combines the research area with multi-source density data, creates a non-parametric carbon emission gridding model of the multi-source remote sensing density data considering different carbon emission acceleration, and uses the model to gridde the carbon emission of the whole large-range research area.
Specifically, step S5 constructs a corresponding generated countermeasure network model according to the partitions in step S4, which is to construct a generated countermeasure network model for each partition obtained by dividing the pointer pair, and then trains the corresponding generated countermeasure network model by using the provincial multi-source density data and the provincial carbon emission data of all provincials contained in each partition.
In step S6, the grid-level multi-source data of different partitions are obtained by resampling the preprocessed multi-source remote sensing data.
In one embodiment, S1 pre-processing the acquired multi-source remote sensing data includes: and projecting, cutting and grid alignment are carried out on the acquired multi-source remote sensing data.
Specifically, after the obtained multi-source remote sensing data are projected, cut and grid aligned, the processed data have consistent coverage (China) and projection modes (Albers and other area projections).
In one embodiment, the multi-source telemetry data includes watertight surface data, air temperature data, night light data, GDP data, and demographic data, and step S2 includes:
respectively carrying out provincial statistics on the preprocessed impervious surface data, night light data, GDP data and population data to generate provincial impervious total area data, provincial night light total amount data, provincial GDP total amount data and provincial population total amount data;
carrying out provincial average processing on the preprocessed air temperature data to generate provincial air temperature data;
the provincial waterproof total area data, the provincial night light total amount data, the provincial GDP total amount data, the provincial population total amount data and the provincial air temperature data form provincial multisource data.
In one embodiment, step S3 includes:
dividing the provincial waterproof total area data, the provincial night light total amount data, the provincial GDP total amount data, the provincial population total amount data and the provincial carbon emission statistical data by each provincial area to generate provincial waterproof density data, provincial luminous density data, provincial GDP density data, provincial population density data and provincial carbon emission density data;
provincial waterproof density data, provincial luminous density data, provincial GDP density data, provincial population density data and preprocessed air temperature data form provincial multisource density data.
Specifically, the provincial level total area data includes the total area data of each provincial level water impermeable, which is divided by the area of each provincial level, so that the provincial level water impermeable density data can be obtained, and other provincial level night light total data and provincial level GDP total data are similar, and are not described herein again.
In one embodiment, step S4 includes:
establishing a time sequence data sequence of carbon dioxide emission data of each province, analyzing the time trend of the carbon dioxide emission quantity of each province in the target year by using Slope analysis, and calculating the following formula:
wherein n is the total number of years involved;is the serial number of the ith year; />Carbon dioxide emission amount of a certain province corresponding to the ith year;
and dividing the carbon emission levels of each province according to the average value and the standard deviation of the Slope to obtain a slow growth zone, a medium speed growth zone, a faster growth zone and a rapid growth zone.
In the specific implementation process, the partition standard is as follows:
is the average value of Slope values; />Is the standard deviation of the Slope value.
In one embodiment, step S5 includes:
for each divided partition, constructing a corresponding generated countermeasure network model as a carbon emission partition meshing model;
dividing the generated provincial multi-source density data and provincial carbon emission density data into a training set and a testing set which correspond to the partition according to a preset proportion;
and respectively training, parameter optimization and verification on the corresponding carbon emission partition gridding model by utilizing the obtained training set and the test set to obtain a trained carbon emission partition gridding model based on the generated countermeasure network.
Specifically, for slow growth zones, medium growth zones, faster growth zones, and rapid growth zones, each partition corresponds to one of the generation of the countermeasure network model.
The preset ratio can be set according to practical situations, such as 8:2,7:3, and the like.
In one embodiment, step S6 includes:
acquiring multi-source remote sensing data in a research area and preprocessing the multi-source remote sensing data;
resampling the preprocessed multi-source remote sensing data to generate grid-level multi-source remote sensing data, wherein the spatial resolution is 1km multiplied by 1km;
and inputting resampled grid-level multisource remote sensing data in the research area into a grid model which is trained in S5 and is based on the carbon emission amount of the generated countermeasure network in a partitioned mode, and outputting a grid-level 1km multiplied by 1km carbon emission spatial distribution map of the whole country.
In a specific implementation process, the multi-source remote sensing data in the research area are 2000, 2005, 2010 and 2015 multi-source remote sensing data of each province contained in China.
In order to more clearly illustrate the specific implementation and effects of the method provided by the present application, the following description is given by way of a specific example:
in this embodiment, the carbon dioxide emission data of each province in China is selected for spatial gridding, the time range is 2000-2018, and data in 2000, 2005, 2010 and 2015 are selected for gridding experimental analysis.
As shown in fig. 1, the application provides a method for carrying out carbon emission partition gridding based on multi-source remote sensing density data, which comprises the following steps:
s1, acquiring provincial carbon emission statistical data and multisource remote sensing data (watertight surface, air temperature, night light, GDP and population) in China 2000-2018, and preprocessing the multisource remote sensing data;
s2, performing provincial multi-source statistics or average calculation on the preprocessed multi-source remote sensing data to generate provincial multi-source data;
s3, performing density conversion on the provincial multi-source data and the provincial carbon emission statistical data to generate provincial multi-source density data and provincial carbon emission density data;
s4, carrying out carbon emission grade division on the provincial carbon emission statistical data, and partitioning a research area according to the carbon emission grade;
s5, constructing a corresponding generated countermeasure network model as a carbon emission partition gridding model according to the partitions in the step S4, and training the generated countermeasure network model by using provincial multi-source density data and provincial carbon emission density data;
and S6, utilizing the carbon emission partition gridding model trained in the S5 and based on the generated countermeasure network to input grid-level multi-source data in a partition mode, and obtaining a national grid-level 1km multiplied by 1km carbon emission spatial distribution map.
Specifically, provincial carbon emission statistics are from the chinese carbon accounting database CEADs; the water impermeable surface data is from the global artificial water impermeable area (GAIA) data product issued by the university of bloom; the air temperature data is from a China 1km resolution month-by-month average air temperature data set provided by a national Qinghai-Tibet plateau science data center; night light data are from two noctilucent remote sensing image data of DMSP/OLS and NPP/VIIRS; the GDP data is from 1km GDP kilometer grid data provided by the national academy of sciences resource environment science data center; the population data is from 1km population grid data provided on the world dpop website adjusted by the united nations;
and establishing a time sequence data sequence of the carbon dioxide emission data of each province, and analyzing the time trend of the carbon dioxide emission amount of each province in the target year by using Slope analysis. In the embodiment of the application, n is 19;number i (year 2000 is the first year, number 1); />Is the carbon dioxide emission amount of a certain province corresponding to the ith year. If the Slope value is greater than 0, it indicates that the carbon dioxide-saving amount of emission increases with time in the period of 2000-2018, and conversely, it indicates that the carbon dioxide-saving amount of emission is in a decreasing trend. The magnitude of the Slope value may then reflect the propensity of the carbon emissions to increase or decrease. And calculating the Slope value of each province in 2000-2018 by using the time trend calculation formula.
The carbon emission level is divided by the average value and standard deviation of slopes of each province, and a slow growth zone, a medium speed growth zone, a faster growth zone and a rapid growth zone are obtained.
Specifically, step S5 includes:
and (3) taking the provincial level multi-source density data in the step (S3) as input data for generating the countermeasure network model, taking the provincial level carbon emission density data as output data, randomly dividing a training set and a testing set according to the proportion of 8:2 and according to the subareas in the step (S4), and training, parameter optimization and verification are carried out on the generated countermeasure network model to obtain a trained generated countermeasure network model. The data formats of the training set and the test set are as follows.
In particular, the method of partitioning employed by the present application has the following advantages:
1. from the viewpoint of model construction, the method mainly has the following characteristics:
(1) The national region can be divided into 4 regions according to the carbon emission levels of each province, namely a slow growth region, a medium speed growth region, a faster growth region and a rapid growth region, and the regions are numbered 1, 2, 3 and 4.
(2) According to partition and 8:2, randomly dividing the data to obtain a training set 1 and a testing set 1, a training set 2 and a testing set 2, a training set 3 and a testing set 3, and a training set 4 and a testing set 4. The data includes provincial multisource density data and provincial carbon emission density. For example, for a rapidly growing region, the provincial multisource density and provincial carbon emission density data contained within the region are randomly partitioned in a 8:2 ratio to yield training set 4 and test set 4.
(3) For each partition, a generation countermeasure network 1, a generation countermeasure network 2, a generation countermeasure network 3, and a generation countermeasure network 4 are respectively constructed.
(4) And respectively inputting the training set and the test set obtained by the partition into the corresponding generated countermeasure model, and training, parameter optimization and verification of the model.
2. From the viewpoint of method effect: compared with the existing method for establishing a unified model for the whole country, the method for modeling the carbon emission partition is designed based on the carbon emission distribution characteristics of different carbon emission growing trends in various provinces of the whole country, so that the problem of large simulation errors of the carbon emission of the model in certain areas caused by unified modeling can be avoided, and the simulation precision and the data reliability of carbon emission meshing can be improved.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the embodiments of the present application without departing from the spirit or scope of the embodiments of the application. Thus, if such modifications and variations of the embodiments of the present application fall within the scope of the claims and the equivalents thereof, the present application is also intended to include such modifications and variations.
Claims (6)
1. The method for carrying out carbon emission partition gridding based on multi-source remote sensing density data is characterized by comprising the following steps of:
s1: acquiring provincial carbon emission statistical data and multisource remote sensing data in a research area, and preprocessing the acquired multisource remote sensing data;
s2: generating provincial multi-source data according to the preprocessed multi-source remote sensing data;
s3: performing density conversion on the provincial multi-source data and the provincial carbon emission statistical data respectively to generate provincial multi-source density data and provincial carbon emission density data;
s4: performing carbon emission grade division on the provincial carbon emission statistical data, and partitioning a research area according to the carbon emission grade;
s5: respectively constructing corresponding generated countermeasure network models according to the subareas in the step S4, serving as a carbon emission subarea gridding model corresponding to each subarea, and training the generated countermeasure network models by using the generated provincial multi-source density data and the provincial carbon emission density data;
s6: inputting grid-level multi-source data of different partitions into a trained carbon emission partition gridding model based on a generated countermeasure network S5 to obtain a national grid-level 1km multiplied by 1km carbon emission spatial distribution map;
wherein, step S4 includes:
establishing a time sequence data sequence of carbon dioxide emission data of each province, analyzing the time trend of the carbon dioxide emission quantity of each province in the target year by using Slope analysis, and calculating the following formula:
wherein n is the total number of years involved;is the serial number of the ith year; />Carbon dioxide emission amount of a certain province corresponding to the ith year;
and dividing the carbon emission levels of each province according to the average value and the standard deviation of the Slope to obtain a slow growth zone, a medium speed growth zone, a faster growth zone and a rapid growth zone.
2. The method for performing carbon emission zoned meshing based on multi-source remote sensing density data according to claim 1, wherein S1 pre-processing the acquired multi-source remote sensing data comprises: and projecting, cutting and grid alignment are carried out on the acquired multi-source remote sensing data.
3. The method for partitioned meshing of carbon emissions based on multi-source remote sensing density data of claim 1, wherein the multi-source remote sensing data comprises watertight surface data, air temperature data, night light data, GDP data, and demographic data, and step S2 comprises:
respectively carrying out provincial statistics on the preprocessed impervious surface data, night light data, GDP data and population data to generate provincial impervious total area data, provincial night light total amount data, provincial GDP total amount data and provincial population total amount data;
carrying out provincial average processing on the preprocessed air temperature data to generate provincial air temperature data;
the provincial waterproof total area data, the provincial night light total amount data, the provincial GDP total amount data, the provincial population total amount data and the provincial air temperature data form provincial multisource data.
4. The method for performing carbon emission zoned meshing based on multi-source remote sensing density data as claimed in claim 3, wherein step S3 comprises:
dividing the provincial waterproof total area data, the provincial night light total amount data, the provincial GDP total amount data, the provincial population total amount data and the provincial carbon emission statistical data by each provincial area to generate provincial waterproof density data, provincial luminous density data, provincial GDP density data, provincial population density data and provincial carbon emission density data;
provincial waterproof density data, provincial luminous density data, provincial GDP density data, provincial population density data and preprocessed air temperature data form provincial multisource density data.
5. The method for performing carbon emission zoned meshing based on multi-source remote sensing density data as claimed in claim 1, wherein step S5 comprises:
for each divided partition, constructing a corresponding generated countermeasure network model as a carbon emission partition meshing model;
dividing the generated provincial multi-source density data and provincial carbon emission density data into a training set and a testing set which correspond to the partition according to a preset proportion;
and respectively training, parameter optimization and verification on the corresponding carbon emission partition gridding model by utilizing the obtained training set and the test set to obtain a trained carbon emission partition gridding model based on the generated countermeasure network.
6. The method for performing carbon emission zoned meshing based on multi-source remote sensing density data as claimed in claim 1, wherein step S6 includes:
acquiring multi-source remote sensing data in a research area and preprocessing the multi-source remote sensing data;
resampling the preprocessed multi-source remote sensing data to generate grid-level multi-source remote sensing data, wherein the spatial resolution is 1km multiplied by 1km;
and inputting resampled grid-level multisource remote sensing data in the research area into a grid model which is trained in S5 and is based on the carbon emission amount of the generated countermeasure network in a partitioned mode, and outputting a grid-level 1km multiplied by 1km carbon emission spatial distribution map of the whole country.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310651468.6A CN116415110B (en) | 2023-06-05 | 2023-06-05 | Method for carrying out carbon emission partition gridding based on multisource remote sensing density data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310651468.6A CN116415110B (en) | 2023-06-05 | 2023-06-05 | Method for carrying out carbon emission partition gridding based on multisource remote sensing density data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116415110A CN116415110A (en) | 2023-07-11 |
CN116415110B true CN116415110B (en) | 2023-08-15 |
Family
ID=87059619
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310651468.6A Active CN116415110B (en) | 2023-06-05 | 2023-06-05 | Method for carrying out carbon emission partition gridding based on multisource remote sensing density data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116415110B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116933934A (en) * | 2023-07-25 | 2023-10-24 | 国网山西省电力公司电力科学研究院 | County carbon emission prediction and analysis method and system integrating VIIRS and statistical data |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106203891A (en) * | 2016-07-28 | 2016-12-07 | 广州地理研究所 | Territorial development density three-dimensional comprehensive evaluation methodology based on Methods on Multi-Sensors RS Image |
CN110704565A (en) * | 2019-09-27 | 2020-01-17 | 泉州师范学院 | Demographic data gridding modeling method based on remote sensing and GIS |
CN111737651A (en) * | 2020-06-22 | 2020-10-02 | 黄河勘测规划设计研究院有限公司 | Spatial gridding drought disaster risk assessment method and system based on multi-source data |
WO2021208393A1 (en) * | 2020-04-15 | 2021-10-21 | 北京工业大学 | Inversion estimation method for air pollutant emission inventory |
CN114461697A (en) * | 2022-01-04 | 2022-05-10 | 武汉理工大学 | Urban carbon emission accounting method based on night lamplight remote sensing and improved STIRPAT |
CN114881466A (en) * | 2022-05-04 | 2022-08-09 | 辽宁工程技术大学 | Multi-source data-based population space partition fitting method |
CN114997480A (en) * | 2022-05-24 | 2022-09-02 | 福州大学 | Low-carbon guide provincial territory space partition optimization simulation method based on MOP-PLUS model |
CN115204618A (en) * | 2022-06-22 | 2022-10-18 | 中国气象科学研究院 | CCMVS regional carbon source convergence inversion evaluation system |
CN115238584A (en) * | 2022-07-29 | 2022-10-25 | 湖南大学 | Population distribution identification method based on multi-source big data |
CN115459349A (en) * | 2022-10-17 | 2022-12-09 | 东南大学溧阳研究院 | Wind, light, water and fire storage multi-source economic-low carbon cooperative scheduling method |
CN115658776A (en) * | 2022-12-05 | 2023-01-31 | 武汉大学 | Method for generating national 1km carbon emission spatial distribution map by combining multi-source data |
CN116109191A (en) * | 2023-02-15 | 2023-05-12 | 中国科学院南京地理与湖泊研究所 | Urban department carbon emission estimation method and system based on satellite observation and GIS |
WO2023095039A1 (en) * | 2021-11-24 | 2023-06-01 | Dendra Systems Ltd. | Generating an above ground biomass density prediction model |
-
2023
- 2023-06-05 CN CN202310651468.6A patent/CN116415110B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106203891A (en) * | 2016-07-28 | 2016-12-07 | 广州地理研究所 | Territorial development density three-dimensional comprehensive evaluation methodology based on Methods on Multi-Sensors RS Image |
CN110704565A (en) * | 2019-09-27 | 2020-01-17 | 泉州师范学院 | Demographic data gridding modeling method based on remote sensing and GIS |
WO2021208393A1 (en) * | 2020-04-15 | 2021-10-21 | 北京工业大学 | Inversion estimation method for air pollutant emission inventory |
CN111737651A (en) * | 2020-06-22 | 2020-10-02 | 黄河勘测规划设计研究院有限公司 | Spatial gridding drought disaster risk assessment method and system based on multi-source data |
WO2023095039A1 (en) * | 2021-11-24 | 2023-06-01 | Dendra Systems Ltd. | Generating an above ground biomass density prediction model |
CN114461697A (en) * | 2022-01-04 | 2022-05-10 | 武汉理工大学 | Urban carbon emission accounting method based on night lamplight remote sensing and improved STIRPAT |
CN114881466A (en) * | 2022-05-04 | 2022-08-09 | 辽宁工程技术大学 | Multi-source data-based population space partition fitting method |
CN114997480A (en) * | 2022-05-24 | 2022-09-02 | 福州大学 | Low-carbon guide provincial territory space partition optimization simulation method based on MOP-PLUS model |
CN115204618A (en) * | 2022-06-22 | 2022-10-18 | 中国气象科学研究院 | CCMVS regional carbon source convergence inversion evaluation system |
CN115238584A (en) * | 2022-07-29 | 2022-10-25 | 湖南大学 | Population distribution identification method based on multi-source big data |
CN115459349A (en) * | 2022-10-17 | 2022-12-09 | 东南大学溧阳研究院 | Wind, light, water and fire storage multi-source economic-low carbon cooperative scheduling method |
CN115658776A (en) * | 2022-12-05 | 2023-01-31 | 武汉大学 | Method for generating national 1km carbon emission spatial distribution map by combining multi-source data |
CN116109191A (en) * | 2023-02-15 | 2023-05-12 | 中国科学院南京地理与湖泊研究所 | Urban department carbon emission estimation method and system based on satellite observation and GIS |
Non-Patent Citations (1)
Title |
---|
中国XCO2时空分布与影响因素分析;莫露,巫兆聪;中国环境科学;2562-2570 * |
Also Published As
Publication number | Publication date |
---|---|
CN116415110A (en) | 2023-07-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109978249B (en) | Population data spatialization method, system and medium based on partition modeling | |
Sun et al. | Estimating the spatial distribution of solar photovoltaic power generation potential on different types of rural rooftops using a deep learning network applied to satellite images | |
CN105205466B (en) | A kind of energy carbon emission amount remote sensing estimation method based on night lights image | |
Pozzer et al. | Mortality attributable to ambient air pollution: A review of global estimates | |
CN106650618A (en) | Random forest model-based population data spatialization method | |
Li et al. | Pattern of spatial evolution of rural settlements in the Jizhou District of China during 1962–2030 | |
CN111896680B (en) | Greenhouse gas emission analysis method and system based on satellite remote sensing data | |
CN116415110B (en) | Method for carrying out carbon emission partition gridding based on multisource remote sensing density data | |
Clarke et al. | Calibrating SLEUTH with big data: Projecting California's land use to 2100 | |
CN110134907B (en) | Rainfall missing data filling method and system and electronic equipment | |
CN111445116A (en) | Auxiliary compiling system for territorial space planning | |
CN110263998A (en) | Multi-source numerical weather forecast set bilayer modification method | |
An et al. | Spatial and temporal evolution of carbon stocks in Dongting Lake wetlands based on remote sensing data | |
CN117036112B (en) | Geographic information system and method for land planning | |
CN113011720B (en) | CA model-based incremental decrement town development boundary defining method | |
CN114398951A (en) | Land use change driving factor mining method based on random forest and crowd-sourced geographic information | |
Fenech et al. | Selecting a global climate model for understanding future projections of climate change | |
CN106815320B (en) | Investigation big data visual modeling method and system based on expanded three-dimensional histogram | |
CN115392137B (en) | Three-dimensional simulation system based on karst water and soil coupling effect that sinks | |
CN112669976A (en) | Crowd health assessment method and system based on ecological environment change | |
Zhang et al. | Understanding archetypal spatial gradient patterns in urban economic, population and air quality nexus: New insights from a geographic-process perspective | |
Long et al. | Mapping parcel-level urban areas for a large geographical area | |
CN116611270A (en) | Typhoon wave real-time aggregate forecasting method, medium and system | |
Li et al. | Knowledge discovery for geographical cellular automata | |
He et al. | Does partition matter? A new approach to modeling land use change |
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 |