CN114330937A - Implicit carbon emission accounting method, device and storage medium - Google Patents
Implicit carbon emission accounting method, device and storage medium Download PDFInfo
- Publication number
- CN114330937A CN114330937A CN202210251674.3A CN202210251674A CN114330937A CN 114330937 A CN114330937 A CN 114330937A CN 202210251674 A CN202210251674 A CN 202210251674A CN 114330937 A CN114330937 A CN 114330937A
- Authority
- CN
- China
- Prior art keywords
- data
- carbon emission
- implicit
- direct
- input
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of environmental protection, and provides a calculation method, equipment and a storage medium for implicit carbon emission2Direct emission data; according to the input-output data and CO2Direct emission data, calculating a driving factor of implicit carbon emission of the target area; accounting for implicit carbon emissions caused by the final demand data based on the driver factors; and correcting the result of the hidden carbon emission through the constructed optimal BP neural network model. This application addresses CO from a consumer perspective2The driving force of emission increase is built through constructing a BP neural network model pairCarbon emissions results are corrected to affect CO2The driving factor of the emission is decomposed into driving factors influencing the change of the implicit carbon emission, and the implicit carbon emission caused by the final demand data is calculated based on the driving factors.
Description
Technical Field
The present application relates to the field of environmental protection technologies, and in particular, to a method, a device, and a storage medium for accounting for implicit carbon emissions based on a BP neural network.
Background
With the development of society and the increase of population, global warming has attracted general attention of countries and the public all over the world, so that the sustainability of the environment faces serious challenges, and a sustainable, green and low-carbon economic model is crucial to reducing energy consumption and carbon emission.
Take the clothing industry as an example. The environment-friendly clothing transfer chain has a complex supply chain as a support industry influencing 'clothing and eating and housing' of people, belongs to the industry with relatively high greenhouse gas emission, and is also worth paying attention to the problem of environmental impact transfer caused by trade activities in the clothing industry. The method has important practical significance for the research of implicit carbon emission accounting and analysis of the carbon emission variation of the textile and clothing industry.
In the past, the life cycle evaluation method (LCA) is mostly adopted to research the influence of environmental emission of the clothes, and the method is mainly focused on CO in the clothes industry caused by clothes production in one country or region2The rapid increase in emissions, this producer perspective can reveal CO due to local production2And the emission changes, and data and technical support are provided for promoting the emission reduction of a producer.
But with the rapid development of economy, the continuous deepening of the trade degree leads to further geographical separation of producers and consumers. This not only allows for an increased degree of integration of supply chains within a region, but also allows for increasingly frequent commodity trade and service exchanges between regions, resulting in a CO2The emission also has certain fluidity, and the CO in the clothing industry driven by regional consumption change caused by the driving of consumption activities cannot be comprehensively considered only through the visual angle of a producer2The amount of emissions varies. How to clarify CO from a consumer perspective2Increase of emission amount, so as to make policy from the view point of consumers to reduce CO in textile and clothing industry2The discharge amount is one of the technical problems which need to be solved at present.
Disclosure of Invention
The main purpose of the present application is to provide a hidden carbon emission based on the consumer's perspectiveThe accounting method, the device, the equipment and the computer readable storage medium correct the result of the hidden carbon-containing emission in the textile and clothing industry by constructing a BP neural network model, improve the accuracy of the hidden carbon-containing accounting, solve the carbon emission driven by consumption activities and the analysis result of the driving factors thereof, and aim to solve the problem of the existing CO2Emissions from the view of the producer alone cannot fully investigate CO driven by consumer activity2The technical problem of the variation of the discharge amount.
In order to achieve the above object, the present application provides a method for accounting for implicit carbon emission, including: obtaining input-output data and CO of target area2Direct emission data; according to the input-output data and CO2Direct emission data, calculating a driving factor of implicit carbon emission of the target area; accounting for implicit carbon emissions caused by the final demand data based on the driver factors; and correcting the result of the hidden carbon emission through the constructed optimal BP neural network model.
In addition, to achieve the above object, the present application also provides a hidden carbon emission amount accounting device including: a data acquisition module for acquiring input-output data and CO of the target area2Direct emission data; the driving factor calculation module is used for calculating a driving factor of the implicit carbon emission of the target area according to the input-output data, wherein the driving factor comprises an industry final demand, a complete consumption coefficient and direct carbon emission intensity; the accounting module is used for accounting the implicit carbon emission caused by the final demand data according to the driving factors; and the correction module is used for correcting the result of the carbon-containing emission through the constructed optimal BP neural network model.
In addition, in order to achieve the above object, the present application further provides an implicit carbon emission amount accounting device, which includes a processor, a memory, and an implicit carbon emission amount accounting program stored on the memory and executable by the processor, wherein when the processor executes the implicit carbon emission amount accounting program, the implicit carbon emission amount accounting method as described above is implemented.
In addition, to achieve the above object, the present application further provides a computer readable storage medium, having a program for calculating the amount of carbon emission implicit stored thereon, wherein when the program for calculating the amount of carbon emission implicit is executed by a processor, the method for calculating the amount of carbon emission implicit as described above is implemented.
The application provides a calculation method for implicit carbon emission, which is used for acquiring input-output data and CO of a target area2Direct emission data; according to the input-output data and CO2Direct emission data, calculating a driving factor of implicit carbon emission of the target area; accounting for implicit carbon emissions caused by the final demand data based on the driver factors; and correcting the result of the hidden carbon emission through the constructed optimal BP neural network model. In this way, the present application clarifies CO from a consumer perspective2The driving force of emission increase is realized, the emission result of the hidden carbon in the textile and clothing industry is corrected by constructing a BP neural network model, the accuracy of the hidden carbon accounting is improved, and then the CO is influenced by adopting an input-output analysis method2Decomposing the driving factor of the emission into driving factors influencing the change of the implicit carbon emission, calculating the implicit carbon emission caused by the final demand data based on the driving factors, and further making carbon emission measures from the perspective of consumers to reduce CO in the target area2And (4) discharging the amount.
These and other aspects of the present application will be more readily apparent from the following description of the embodiments. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application.
In the drawings:
FIG. 1 is a schematic flow chart of a first embodiment of a method for accounting for the amount of carbon emissions implicit in the present application;
FIG. 2 is a schematic flow chart of a second embodiment of the method for accounting for the amount of carbon emissions contained herein;
FIG. 3 is a diagram of a basic structure of a Chinese input-output table according to a second embodiment of the present invention;
FIG. 4 is a schematic flow chart of a third embodiment of the calculation method for the implicit carbon emission;
FIG. 5 is a schematic structural diagram of a BP neural network model according to a fourth embodiment of the present application of the calculation method for implicit carbon emission;
FIG. 6 is a schematic flow chart of the method for accounting the carbon emission amount;
FIG. 7 is a functional block diagram of a first embodiment of an apparatus for accounting for carbon emissions implicit in the present application;
FIG. 8 is a block diagram schematically illustrating the structure of the carbon emission implicit accounting apparatus according to the present invention.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
The present application is further described with reference to the accompanying drawings and the detailed description, and it should be noted that, in the present application, the embodiments or technical features described below may be arbitrarily combined to form a new embodiment without conflict.
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
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, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
The embodiment of the application provides a method, equipment and a storage medium for accounting implicit carbon emission, which are different from the prior method that a life cycle evaluation method is adopted only from the perspective of a producer to disclose CO caused by local production2The emissions change, but the CO can be clarified from the consumer perspective2The emission growth driving force is established, the emission result of the hidden carbon-containing substances in the textile and clothing industry is corrected by constructing a BP neural network model, the accuracy of the hidden carbon-containing calculation is improved, and further, the CO is influenced by a structural decomposition analysis method based on input-output analysis2Decomposing the emission factors, analyzing the driving factors influencing the carbon emission change, making explicit the carbon emission and the driving factors influencing the carbon emission change, and further making policy from the perspective of consumers to reduce CO2And (4) discharging the amount. In some embodiments, the implicit carbon emission accounting method may be applied to an implicit carbon emission accounting device, which may be a device with display and processing functions, such as a PC, a portable computer, a mobile terminal, or the like, but is not limited thereto.
Referring to fig. 1, fig. 1 is a schematic flow chart of a first embodiment of a method for accounting for carbon emissions implicitly according to the present application. In an embodiment of the application, the method for accounting the emission of the hidden carbon comprises the following steps:
step S10, obtaining input-output data and CO of the target area2Direct emissions data.
In some embodiments, the input-output data includes input data, final demand data, and gross production data for the target area.
The target area may be divided according to countries, regions, cities, or districts, and may be determined according to actual accounting requirements. Illustratively, the target region may be a country or region for acquiring CO due to production and consumption in the country or region2Input-output data for rapid growth of emissions.
In some embodiments, the obtaining input-output data of the target area includes: and taking the year as a statistical unit, counting input-output data in a target area collected by each economic department, and collecting the input data, the final demand data and the total output value data of the target area as the input-output data of the target area.
Step S20, according to the input-output data and CO2Direct emissions data, calculating a driving factor for the target area that implies carbon emissions.
In some embodiments, the driving factors include industry end demand, total consumption coefficient, and direct carbon emission intensity.
And summarizing the driving factors influencing the implicit carbon emission into three aspects of final industry requirements, a complete consumption coefficient and direct carbon emission intensity, and analyzing the influence of the driving factors such as the final industry requirements, the complete consumption coefficient and the direct carbon emission intensity on the carbon emission change.
Step S30, calculating the implicit carbon emissions caused by the final demand data based on the driving factor.
In some embodiments, the implicit carbon emissions driven by the final demand data are accounted from the consumer perspective, supported by the input-output data for the target area, namely: the total amount of carbon emissions resulting from the final demand is accounted for.
And step S40, correcting the result of the hidden carbon emission through the constructed optimal BP neural network model.
In the embodiment of the application, the relevant index data obtained in the step S10 is input into the constructed BP neural network model, and the output variable is the error between the predicted implicit carbon value and the true value, so that the true value result of the implicit carbon emission amount calculated in the step S30 is corrected.
According to the calculation method for the implicit carbon emission, input-output data and CO of a target area are obtained2Direct emission data; according to the input-output data and CO2Direct emission data, calculating a driving factor of implicit carbon emission of the target area; accounting for implicit carbon emissions caused by the final demand data based on the driver factors; and correcting the result of the hidden carbon emission through the constructed optimal BP neural network model. In this way, the present application clarifies CO from a consumer perspective2The driving force of emission increase is realized, the emission result of the hidden carbon in the textile and clothing industry is corrected by constructing a BP neural network model, the accuracy of the hidden carbon accounting is improved, and then the CO is influenced by adopting an input-output analysis method2Decomposing the driving factor of the emission into driving factors influencing the change of the hidden carbon emission, calculating the hidden carbon emission caused by the final demand data based on the driving factors, and further making carbon emission measures from the perspective of consumers to reduce CO in the textile and clothing industry of the target area2And (4) discharging the amount.
Referring to fig. 2, fig. 2 is a schematic flow chart of a second embodiment of the method for calculating the amount of carbon emissions implicit in the present application.
Based on the foregoing embodiment shown in fig. 1, in the embodiment of the present application, in step S20, the method for accounting the amount of carbon emission further includes:
s201, acquiring input quantity data and total output data of a target area in the input-output data;
s202, calculating a direct consumption coefficient according to the input data and the total production data;
and S203, calculating a complete consumption coefficient according to the direct consumption coefficient.
Wherein the direct consumption coefficient is calculated according to the formula: a isij=Zij/XiIn the formula, ZijData representing the input amount, XiRepresenting total production data, aijRepresents the direct consumption coefficient, i, j ∈ 1,2 … n, n represents the number of economic sectors.
Wherein, the calculation formula of the complete consumption coefficient L is as follows: l = (I-A)-1Wherein L represents a total consumption coefficient, I represents a unit matrix, and A = aij，aijRepresenting the direct consumption coefficient.
For example, in the domestic clothing industry of China, CO is caused by production and consumption2The rapid increase in the amount of emissions is an example. Before the input quantity data and the total output value data of the target area are obtained, input-output tables of 42 economic departments in the whole country in 2012, 2015 and 2017 are respectively obtained according to a Chinese input-output table issued by national economic accounting department of the national statistical office. Among the 42 sectors, the sector of textile and clothing, which is required for the research of the clothing industry, is shown in fig. 3.
In some embodiments, the input amount data Z according to the target areaijFinal demand data YiAnd total numerical data XiSatisfy the balance formula:
∑i,j∈1,2…42Zij+∑i∈1,2…42Yi=Xi（1）
in the formula, input amount data Zij(i, j ∈ 1,2 … n) represents the amount of product required to be invested in department i to produce department j; final demand data Yi(i e 1,2 … n) represents the end use requirements of n economic departments, total production value data Xi(i e 1,2 … 42) represents the total value of n economic sectors.
For example, in the domestic clothing industry of China, CO is caused by production and consumption2The rapid increase in the amount of emissions is an example. In the table of input and output of 42 economic departments in China, Zij(i, j ∈ 1,2 … 42) represents the required input for producing j productAmount of product, Yi(i e 1,2 … 42) represents the final demand of 42 economic departments, X respectivelyi(i e.1, 2 … 42) represents the total yield of 42 economic sectors, respectively, and the balance (1) is satisfied between the three. Then define the direct consumption coefficient a according to the balance equation (1)ij=Zij/XiDirect coefficient of consumption aijRepresenting the amount of product i required to be input into the production process for producing the product of unit j.
In some embodiments, said method further comprises the step of, between said final demand data and total production data and said full consumption coefficient:
X=(I-A)-1Y （2）
wherein X = Xi, A=aij, Y=Yi,L=（I-A）-1，XiData representing total production in the target area, aijDenotes the direct consumption coefficient, YiRepresenting the final demand data and L representing the full consumption factor.
In some embodiments, the complete consumption factor L implies direct and indirect input into the final product production process.
In particular, since the input-output tables are all value-type input-output tables expressed by the current-year price, the current-year-price input-output tables can reflect the total economic quantity, technical conditions, industrial structures and the like based on the current-year price, and cannot reflect the change of main economic variables after removing price variation factors for a period of time. Therefore, in order to eliminate the influence of price factors on research and enhance the comparability of data, the input-output table of the current year price needs to be converted into the comparable input-output table, so that the complicated economic-technical relation among all departments of national economy can be reflected more truly, and the industrial structure and the economic growth change situation can be represented more accurately.
In some embodiments, the current-year-price input-output table may be converted to a comparable-price input-output table using an existing input-output table and corresponding Producer Price Index (PPI), such as: defining 2012 as a base year of price, and reducing all monetary data by using different Producer Price Indices (PPIs) to reduce 42 currency dataThe departments are divided into four categories, namely agriculture, industry, building industry and service industry. Wherein agriculture is reduced according to the agricultural product production price index; reducing the industrial rate according to the factory price index of industrial branch manufacturers; the construction industry is reduced according to the fixed asset investment price index of the construction industry installation project; the service industry is reduced according to the third industry added value index or the resident consumption price index. Resulting in a input-output table that can be used for consistent analysis from 2012 to 2017. Thus, the total yield X of each department in 2012, 2015 and 2017 including the department of textile and clothing can be respectively obtainedi。
It is worth noting that when focusing on the environmental impact of the final consumption of the textile and clothing industry, for example, which belongs to the 7 th department among the 42 economic departments nationwide, the final demand Y of the other departments is therefore the focusi(i ∉ 7) is 0, i.e. the final expenditure for consumption by the other departments is set to zero.
Referring to fig. 4, fig. 4 is a schematic flow chart of a third embodiment of the calculation method for the amount of carbon emission hidden in the present application.
Based on the foregoing embodiment shown in fig. 2, in the embodiment of the present application, in step S30, the method for accounting the amount of carbon emission further includes:
s301, acquiring CO in a target area2Direct discharge and total production data in the target area;
s302, according to the CO2Direct carbon emissions intensity was calculated from the direct emissions and total yield data.
Wherein, the calculation formula of the direct carbon emission intensity is as follows:
e=E/X （3）
wherein E represents CO in the target region2Direct discharge; x represents total output data in a target area; e represents the direct carbon emission intensity.
In some embodiments, for example, the CO related to the above economic sector in 2012, 2015 and 2017 of china may be obtained through the CEADs database2Discharge data including and according to the Chinese textile garment departmentYield and CO2The direct carbon emission intensity was calculated based on the formula (3).
In an embodiment of the present application, in the step S30, the implicit carbon emission caused by the final demand data is calculated based on the driving factor, and the calculation formula of the implicit carbon emission is as follows:
where CE represents the amount of implicit carbon emissions caused by the final demand data,
a diagonalized matrix representing the direct carbon emission intensity e; i represents an identity matrix, A represents a direct consumption coefficient matrix; l = (I-A)-1Representing a matrix of full consumption coefficients; y iscloRepresenting the industry ultimate needs.
Illustratively, CE represents the implicit carbon emissions caused by the final demand data. Namely: representing the total carbon emission caused by the final requirement of the China textile and clothing industry through the national textile and clothing industry chain, namely the complete carbon emission of the national textile and clothing industry; the method comprises direct discharge and indirect discharge, wherein the direct carbon discharge refers to carbon discharge caused by direct consumption of various energy sources in the production process of the clothing industry, and the indirect discharge refers to carbon discharge of other departments in the textile and clothing industry chain besides the textile and clothing industry.
Illustratively, when the present application focuses on the environmental impact of the final consumer in the textile apparel industry in china, the final demand of the other sector is 0, which represents the final demand of the textile apparel industry.
In some embodiments, the step S30 is preceded by a structural decomposition analysis of the implied carbon footprint. The Structure Decomposition Analysis (Structure Decomposition Analysis) method represents the change of a certain target variable by the sum of the changes of several independent variables of the economic system under the support of input and output data, and considers the contribution of each independent variable in the target variable.
In some embodiments, referring to fig. 5 and 6, the constructed optimal BP neural network model includes:
determining an input layer input variable, a hidden layer neuron number and an output layer output variable of the BP neural network;
and constructing an initial BP neural network model, and training and correcting to obtain an optimal BP neural network model.
Referring to fig. 5, fig. 5 is a schematic diagram of constructing an initial BP neural network model. And obtaining a BP neural network model to be trained. Since the bp (back propagation) neural network is a multi-layer feedforward neural network trained according to an error back propagation algorithm, it is one of the most widely used neural network models. The method solves the problem that a simple sensor cannot solve by utilizing the arbitrary complex mode classification capability and the excellent multidimensional function mapping capability of the BP neural network.
The BP neural network model to be trained is provided with an input layer (input layer), a hidden layer (hide layer) and an output layer (output layer), and specifically comprises input variables of the input layer, the number of neurons in the hidden layer and output variables of the output layer.
In the embodiment of the present application, the input variables include direct carbon emission (E), total yield (X), Leontief inverse matrix (L), and final cost (Y) of the textile and clothing industry.
The number of the neurons of the hidden layer is
Wherein x is the number of neurons in the input layer, y is the number of neurons in the output layer, and b is [1,10 ]]Constant term in between.
The number of the neurons of the output layer is 1, and the output variable is the hidden carbon emission of the clothing industry department.
In some embodiments, the initial BP neural network model is trained.
After an initial BP neural network model is built, a BP neural network training stage is started, wherein the BP neural network training process comprises inputting original data and building a function mapping relation between an input layer and an output layer of the neural network. Since neurons pass through the activation function, the mapping relation between the input variable and the output variable is obtained by introducing the activation function sigmod function, and the following formula is shown:
and accordingly writing an output function of the hidden layer neuron:
wherein u isjTo hide the output of neurons, f is the mapping of the activation function, vijWeights for the ith input variable and the jth hidden layer neuron, θu jThe threshold value of the jth neuron of the hidden layer u, namely the bias term.
After the function mapping relationship between the input layer and the output layer is determined, a training data set is established and input into the BP neural network model by taking the input-output data obtained in the step S10 as basic data, and the BP neural network is trained and stored by using the determined function mapping relationship to obtain the trained BP neural network model.
In some embodiments, the method further comprises correcting the trained BP neural network model, and the correcting process comprises:
firstly, obtaining a predicted value through forward propagation activation of the trained BP neural network model; then, gradient adjustment is carried out on the coefficient by a gradient descent method through back propagation to obtain a corrected value; and finally, predicting the trained BP neural network model, and checking the model prediction effect through accuracy.
The hidden layer neuron and the output layer neuron activation functions adopted by the application are sigmod functions, and a forward propagation formula is obtained:
wherein y is a predicted value, and the application refers to the hidden carbon emission CE, W of the China textile and clothing industryjWeights for the jth hidden layer neuron and the output variable y; thetayIs a bias of y.
After the predicted value of the carbon emission hidden in the textile and clothing industry of China is obtained through the formula, the coefficient is subjected to gradient adjustment through back propagation to obtain a corrected value, the error back propagation formula specifically means that an error is calculated through a difference value of an output value, the error is reduced along the direction of the coefficient each time, namely, the error is reduced towards the direction of a guide number (namely, a gradient) until an optimal value is obtained, u is set as a reduction speed, namely, a learning rate, y is a target variable, and w is a parameter to be optimized, then:
the inverse gradient descent formula is:
finally, correcting the trained BP neural network model through the prediction effect of the accuracy rate test model, so that the error between the true value of the hidden carbon emission in the China clothing industry and the predicted value of the network is as small as possible, and the specific objective function is as follows:
wherein v isij，θu j，wj，θyJ is an optimization parameter of the objective function which can adopt a gradient descent method for the network parameter needing to be determined. And finally obtaining the optimal output layer variable through continuous iteration, thereby obtaining the optimal BP neural network model.
After the optimal BP neural network model is obtained, the index data of the input and output data related to the step S10 is input into the constructed optimal BP neural network model, and the output variable is the optimal error value of the carbon hidden predicted value and the true value in the China textile and clothing industry, so that the true value is corrected.
In some embodiments, the industry end needs include product consumption needs, average human consumption needs, and population size, and the drivers after the industry end needs are decomposed include: product consumption needs, per-capita consumption needs, population size, total consumption coefficient, and direct carbon emission intensity.
The accounting method for the hidden carbon emission amount further comprises the following steps: and acquiring a driving factor after the final requirement decomposition of the industry, taking the arithmetic mean of all solutions of the carbon emission calculated by decomposing and unfolding the driving factor as a final solution of the implicit carbon emission, identifying the influence degree of the change of the driving factor on the change of the implicit carbon emission, and formulating the carbon emission measure of a target area.
Illustratively, the present application uses this to study the driving factors that influence the variation of the carbon emissions implicit in the textile and clothing sector and generalize it into three main aspects: 1) carbon emission intensity effect, expressed as direct carbon emission intensity e; 2) production technology effects are expressed by a complete consumption coefficient matrix L; 3) final requirement of clothing industry, using YcloAnd (4) showing.
Among them, the final demand of the clothing industry YcloExpressed in a matrix as follows:
then there are:
and:
the following equation is obtained:
namely:
。
among them, the final demand of the clothing industry YcloFurther decomposed into a clothing consumption demand structure YscloFinal demand Y for Rensheng clothingvcloAnd population size p.
According to the basic idea of structural decomposition analysis, the total carbon emission driven by the final demand of the Chinese clothing industry can be decomposed as follows:
（6）
the second step expression of the formula (6) represents the influence of the variation of each independent variable on the variation of the target variable CE, the last step expression of the formula (6) is a supplement to the previous step expression, and the last step expression further represents that only one target variable is changed by controlling other independent variables to be unchanged, the sum of the influences of the variations of different driving factors on the variation of the target variable CE is researched, and the CE and the variable in brackets are integrated and are not related to the formula (5).
In addition, the total carbon emissions driven by the final demand of the chinese clothing industry can also be broken down as follows:
△CE=CE1-CE0=E1L1Ysclo1YVcolo1P1-E0L0YSclo0P0=△E*wE+△L*wL+△Ysclo*wsclo+△Yvclo*wvclo+△P*WP (7)
wherein subscripts 1 and 0 represent calculated year and reference year, respectively, WE、WL、Wsclo、WVclo、WPRespectively representing carbon emission intensity effect e, industrial structure effect L and clothing consumption demand structure YscloFinal demand Y for Rensheng clothingvcloAnd a weight of population size P.
Therefore, the weight in equation (7) can be solved as follows:
（8）
the solution to the weight is, according to equation (8):
however, the above is only a weighted solution, and by changing the permutation and combination of the five variables in equation (7), different solutions can be obtained, and for the variables with n drivers, n | solutions are generated, and for the variables with 5 drivers, there are 5 | solutions, i.e. 120 solutions.
In yet another embodiment of the present application, to solve the multiple solution problem, the present application adopts the mirror decomposition method of the two-stage Dietzenbacher and Loss method by considering all the structural decomposition expansions, i.e. by combining the carbon emission intensity effect e, the industrial structural effect L, the clothing consumer demand structure YscloUniform garment for everyoneUltimate demand YvcloAnd the arithmetic mean of all solutions of the population size P is used as a final solution, so that the influence degree of the change of each driving factor on the carbon emission change of the China clothing industry is identified, and the formula is as follows:
（9）
（10）
（11）
（12）
（13）
wherein the determination of the numbers (e.g., 24, 6, 4) in the above equations (9) - (13) is determined by the weight of the driving factor in all structural expansions.
△CEE、△CEL、△CESclo、△CEVcloAnd Δ CEpRespectively representing the influence factors of the carbon emission intensity change, the industrial structure technology adjustment change, the final demand structure change of the clothing industry, the final demand change of the average person clothing and the population scale change of the carbon emission change of the textile clothing industry in China.
In addition, the embodiment of the application also provides a device for accounting the implicit carbon emission.
Referring to fig. 7, fig. 7 is a functional block diagram of a first embodiment of the device for calculating the amount of carbon emissions implicit in the present application.
In an embodiment of the present application, the device for accounting for the amount of carbon emission includes:
a data acquisition module 10 for acquiring input-output data and CO of the target area2Direct emission data;
a driving factor calculating module 20, configured to calculate a driving factor of the target area, which implies carbon emission according to the input-output data, where the driving factor includes an industry final demand, a complete consumption coefficient, and a direct carbon emission intensity;
an accounting module 30, configured to account, according to the driving factor, an implicit carbon emission caused by the final demand data; and
and the correcting module 40 is used for correcting the result of the carbon-containing emission through the constructed optimal BP neural network model.
Each module in the device for accounting the carbon-containing emission corresponds to each step in the embodiment of the method for accounting the carbon-containing emission, and the functions and the implementation process of the device are not described in detail herein.
The implicit carbon emission amount accounting method and apparatus of the present application may be implemented in the form of a computer program, which may be run on an implicit carbon emission amount accounting device as shown in fig. 8.
Referring to fig. 8, fig. 8 is a schematic block diagram of a structure of an equipment for accounting for the amount of carbon emissions.
Referring to fig. 8, the implicit carbon emission amount accounting apparatus includes a processor and a memory connected by a system bus, wherein the memory may include a nonvolatile storage medium and an internal memory.
The processor is used for providing calculation and control capacity and supporting the operation of the whole implicit carbon emission accounting equipment.
The internal memory provides an environment for running a computer program in the non-volatile storage medium, which when executed by the processor causes the processor to perform any of the implicit carbon emission accounting methods.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The processor is configured to run a computer program stored in a memory to implement the embodiments of the method for accounting for carbon emission implicitly according to the present application, which is not described herein again.
In addition, the embodiment of the application also provides a computer readable storage medium.
The computer readable storage medium stores an implicit carbon emission accounting program, wherein when the implicit carbon emission accounting program is executed by a processor, the steps of the implicit carbon emission accounting method are realized.
The method implemented when the implicit carbon emission amount accounting program is executed may refer to various embodiments of the implicit carbon emission amount accounting method of the present application, and will not be described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (10)
1. The method for accounting the hidden carbon emission is characterized by comprising the following steps of:
obtaining input-output data and CO of target area2Direct emission data;
according to the input-output data and CO2Direct emission data, calculating a driving factor of implicit carbon emission of the target area;
accounting for implicit carbon emissions caused by the final demand data based on the driver factors;
and correcting the result of the hidden carbon emission through the constructed optimal BP neural network model.
2. The method of claim 1, wherein the input-output data includes input data, final demand data, and total production data for the target area; the driving factors include industry end demand, total consumption coefficient, and direct carbon emission intensity.
3. The implicit carbon emission accounting method according to claim 2, further comprising:
acquiring input quantity data and total production value data in the input-output data;
calculating a direct consumption coefficient according to the input data and the total output data, wherein the calculation formula of the direct consumption coefficient is as follows: a isij=Zij/XiIn the formula, ZijData representing the input amount, XiRepresenting total production data, aijRepresenting the direct consumption coefficient, i, j ∈ 1,2 … n, n representing the number of economic departments;
calculating a complete consumption coefficient according to the direct consumption coefficient, wherein the calculation formula of the complete consumption coefficient L is as follows: l = (I-A)-1Wherein L represents a total consumption coefficient, I represents a unit matrix, and A = aij，aijRepresenting direct consumption coefficient。
4. The method of claim 3, wherein the target area investment data Z isijFinal demand data YiAnd total numerical data XiSatisfy the balance formula:
∑i,j∈1,2…42Zij+∑i∈1,2…42Yi=Xiin the formula, input amount data Zij(i, j ∈ 1,2 … n) represents the amount of product required to be invested in department i to produce department j; final demand data Yi(i e 1,2 … n) represents the end use requirements of n economic departments, total production value data Xi(i e 1,2 … 42) represents the total value of n economic sectors.
5. The implicit carbon emissions accounting method of claim 4, wherein the full consumption coefficient and the final demand data and total production data further satisfy:
X=(I-A)-1Y
wherein X = Xi, A=aij, Y=Yi, L=（I-A）-1，XiData representing total production in the target area, aijDenotes the direct consumption coefficient, YiRepresenting the final demand data and L representing the full consumption factor.
6. The implicit carbon emission accounting method of claim 1, wherein the method comprises:
obtaining CO in a target area2Direct discharge and total production data in the target area;
according to the CO2Calculating direct carbon emission intensity according to the direct emission and the total output value data; wherein the calculation formula of the direct carbon emission intensity is as follows:
e=E/X
wherein E represents CO in the target region2Direct discharge; x represents total output data in a target area; e represents the direct carbon emission intensity.
7. The implicit carbon emission accounting method according to claim 6, wherein the implicit carbon emission caused by the final demand data is accounted based on the driving factor, and the implicit carbon emission is calculated by the following formula:
where CE represents the amount of implicit carbon emissions caused by the final demand data,
a diagonalized matrix representing the direct carbon emission intensity e; i represents an identity matrix, A represents a direct consumption coefficient matrix; l = (I-A)-1Representing a matrix of full consumption coefficients; y iscloRepresenting the industry ultimate needs.
8. The implicit carbon emission accounting method according to any one of claims 1 to 7, wherein the constructed optimal BP neural network model comprises:
determining an input layer input variable, a hidden layer neuron number and an output layer output variable of the BP neural network;
and constructing an initial BP neural network model, and training and correcting to obtain an optimal BP neural network model.
9. An implicit carbon emission amount accounting apparatus comprising a processor, a memory, and an implicit carbon emission amount accounting program stored on the memory and executable by the processor, wherein the implicit carbon emission amount accounting program when executed by the processor implements the steps of the implicit carbon emission amount accounting method according to any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon an implicit carbon emission amount accounting program, wherein the implicit carbon emission amount accounting program, when executed by a processor, implements the steps of the implicit carbon emission amount accounting method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210251674.3A CN114330937A (en) | 2022-03-15 | 2022-03-15 | Implicit carbon emission accounting method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210251674.3A CN114330937A (en) | 2022-03-15 | 2022-03-15 | Implicit carbon emission accounting method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114330937A true CN114330937A (en) | 2022-04-12 |
Family
ID=81033388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210251674.3A Pending CN114330937A (en) | 2022-03-15 | 2022-03-15 | Implicit carbon emission accounting method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114330937A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115147012A (en) * | 2022-08-31 | 2022-10-04 | 南方电网数字电网研究院有限公司 | Carbon emission accounting method and device based on neural network model |
| CN115600840A (en) * | 2022-12-07 | 2023-01-13 | 南方电网数字电网研究院有限公司（Cn） | User group carbon emission dynamic portrait model construction method, device and equipment |
| CN116362518A (en) * | 2023-04-04 | 2023-06-30 | 无锡物联网创新中心有限公司 | Spinning cotton distribution method and related device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105975799A (en) * | 2016-06-01 | 2016-09-28 | 广东电网有限责任公司电力科学研究院 | Method and system for calculating carbon emissions |
| CN108629722A (en) * | 2018-04-28 | 2018-10-09 | 河海大学 | A kind of SO2Discharge Driving Forces quantization method |
| CN111126827A (en) * | 2019-12-19 | 2020-05-08 | 广东工业大学 | Input-output accounting model construction method based on BP artificial neural network |
-
2022
- 2022-03-15 CN CN202210251674.3A patent/CN114330937A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105975799A (en) * | 2016-06-01 | 2016-09-28 | 广东电网有限责任公司电力科学研究院 | Method and system for calculating carbon emissions |
| CN108629722A (en) * | 2018-04-28 | 2018-10-09 | 河海大学 | A kind of SO2Discharge Driving Forces quantization method |
| CN111126827A (en) * | 2019-12-19 | 2020-05-08 | 广东工业大学 | Input-output accounting model construction method based on BP artificial neural network |
Non-Patent Citations (2)
| Title |
|---|
| 吴英娜等: "中美进出口贸易中隐含碳的研究――基于贸易污染条件的分析", 《宏观经济研究》 * |
| 赵敏怡: "全球服装行业贸易隐含碳排放及驱动因素分析", 《万方数据》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115147012A (en) * | 2022-08-31 | 2022-10-04 | 南方电网数字电网研究院有限公司 | Carbon emission accounting method and device based on neural network model |
| CN115600840A (en) * | 2022-12-07 | 2023-01-13 | 南方电网数字电网研究院有限公司（Cn） | User group carbon emission dynamic portrait model construction method, device and equipment |
| CN116362518A (en) * | 2023-04-04 | 2023-06-30 | 无锡物联网创新中心有限公司 | Spinning cotton distribution method and related device |
| CN116362518B (en) * | 2023-04-04 | 2023-12-19 | 无锡物联网创新中心有限公司 | Spinning cotton distribution method and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Using Bayesian deep learning to capture uncertainty for residential net load forecasting | |
| CN114330937A (en) | Implicit carbon emission accounting method, device and storage medium | |
| Xu et al. | Accurate and interpretable bayesian mars for traffic flow prediction | |
| Li et al. | Demand prediction and regulation zoning of urban-industrial land: Evidence from Beijing-Tianjin-Hebei Urban Agglomeration, China | |
| Dumitru et al. | Solar photovoltaic energy production forecast using neural networks | |
| Magliocca et al. | From meta-studies to modeling: Using synthesis knowledge to build broadly applicable process-based land change models | |
| CN106251174A (en) | Information recommendation method and device | |
| Chai et al. | A decomposition–integration model with dynamic fuzzy reconstruction for crude oil price prediction and the implications for sustainable development | |
| CN110837921A (en) | Real estate price prediction research method based on gradient lifting decision tree mixed model | |
| CN101630376A (en) | Soft-sensing modeling method and soft meter of multi-model neural network in biological fermentation process | |
| Szeląg et al. | Soft sensor application in identification of the activated sludge bulking considering the technological and economical aspects of smart systems functioning | |
| Ding et al. | A prediction model of the sum of container based on combined BP neural network and SVM | |
| Wu et al. | Wavelet fuzzy cognitive maps | |
| Tung et al. | Binary classification and data analysis for modeling calendar anomalies in financial markets | |
| Ketipi et al. | A flexible nonlinear approach to represent cause–effect relationships in FCMs | |
| CN115099450A (en) | Family carbon emission monitoring and accounting platform based on fusion model | |
| Zhao et al. | MFCNV: a new method to detect copy number variations from next-generation sequencing data | |
| Harrou et al. | Energy consumption prediction in water treatment plants using deep learning with data augmentation | |
| Zhang et al. | Precise marketing data mining method of E-commerce platform based on association rules | |
| Nguyen et al. | An extensive investigation on leveraging machine learning techniques for high-precision predictive modeling of CO2 emission | |
| CN116187823A (en) | Regional carbon emission calculation method and device based on electric power data | |
| Tang et al. | Forecasting annual foreign tourist arrivals to China by incorporating firefly algorithm into fractional non-homogenous discrete Grey model | |
| Zhao et al. | A novel cryptocurrency price time series hybrid prediction model via machine learning with MATLAB/Simulink | |
| Xiong et al. | The housing demand analysis and prediction of the real estate based on the AWGM (1, N) model | |
| CN112686470A (en) | Power grid saturation load prediction method and device and terminal equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220412 |