STIRPAT model-based carbon emission prediction method, apparatus and device, and medium
Through the carbon emission prediction method based on the STIRPAT model, combined with the ElasticNet method, decision tree method and ridge regression analysis, the influencing factor analysis model was screened and constructed, and the uncertainty and unreliability of carbon emission prediction in the existing technology was solved, and the problem of carbon emission prediction in the existing technology was realized. More accurate carbon emission forecasts and guidance on low-carbon development strategies.
Patent Information
- Application Number
- CN202411543781.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2025-02-11
AI Technical Summary
Existing carbon emission forecasting methods are difficult to ensure the authenticity and reliability of carbon emission peak and peak time when dealing with uncertainties in influencing factors and future risk changes.
Using the carbon emission prediction method based on the STIRPAT model, the carbon emissions and carbon emission intensity data of each province were obtained, combined with the ElasticNet method, decision tree method and ridge regression analysis, the influencing factor analysis model was screened and constructed to obtain the carbon emissions of each province. and predicted values of carbon emission intensity.
This method can limit the dual-control forecast of carbon emissions to a relatively limited and dynamic range, improve the authenticity and reliability of carbon emissions and carbon emission intensity, and provide more accurate guidance for provinces to formulate low-carbon development strategies. hour.
Smart Images
Figure CN119417047A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of carbon emission reduction coordination optimization, and in particular to a carbon emission prediction method, device, equipment and medium based on a STIRPAT model. Background Art
[0002] At present, carbon emission prediction methods are mainly studied from the perspectives of research scale, carbon emission measurement, influencing factors and predicted carbon peak. There are few predictions on the uncertainty of influencing factors and future risk changes. Therefore, the authenticity and reliability of the obtained carbon emission peak and peak time need to be strengthened. Summary of the invention
[0003] The purpose of the present invention is to provide a carbon emission prediction method, device, equipment and medium based on the STIRPAT model, which can limit the carbon emission dual control prediction to a relatively limited and dynamically changing range, and improve the authenticity and reliability of carbon emissions and carbon emission intensity.
[0004] According to one aspect disclosed in the present invention, a carbon emission prediction method based on the STIRPAT model is provided, including: obtaining data on influencing factors of carbon emissions and carbon emission intensity of each province, and performing data processing on the influencing factor data; using the ElasticNet method to screen the influencing factors of carbon emissions and carbon emission intensity of each province to obtain the initial screening results; constructing a model for the influencing factors screened initially to obtain an influencing factor analysis model based on the STIRPAT model; performing ridge regression analysis on the STIRPAT model to obtain the fitting coefficient of the model; performing ridge regression on the influencing factors to obtain the elasticity coefficients of the influencing factors of carbon emissions and carbon emission intensity of each province, and predicting the carbon emissions and carbon emission intensity of each province through the elasticity coefficients.
[0005] According to the second aspect of the present disclosure, a carbon emission prediction device based on the STIRPAT model is provided, characterized in that it includes: a data acquisition module, which is used to obtain the influencing factor data of carbon emissions and carbon emission intensity of each province, and perform data processing on the influencing factor data; a screening module, which is used to screen the influencing factors of carbon emissions and carbon emission intensity of each province by using the ElasticNet method to obtain the initial screening results; a model construction module, which is used to construct a model for the influencing factors screened initially, and obtain an influencing factor analysis model based on the STIRPAT model; a model analysis module, which is used to perform ridge regression analysis on the STIRPAT model to obtain the fitting coefficient of the model; a prediction module, which is used to perform ridge regression on the influencing factors to obtain the elasticity coefficients of the influencing factors of carbon emissions and carbon emission intensity of each province, and predict the carbon emissions and carbon emission intensity of each province through the elasticity coefficients.
[0006] According to a third aspect of the present disclosure, an electronic device is provided, comprising a processor, and a memory and a network interface connected to the processor; the network interface is connected to a non-volatile memory in a server; when the processor is running, it retrieves a computer program from the non-volatile memory through the network interface, and runs the computer program through the memory to execute the carbon emission prediction method based on the STIRPAT model as described above.
[0007] According to a fourth aspect of the present disclosure, a storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the carbon emission prediction method based on the STIRPAT model as described above is implemented.
[0008] It can be seen from the above technical scheme that the present disclosure proposes a carbon emission prediction method based on the STIRPAT model. The decision tree method, ElasticNet method and ridge regression are used to ensure that the screening results of the influencing factors of carbon emissions and carbon emission intensity of each province are reasonable, and the effectiveness of the STIRPAT model is proved through empirical analysis. The carbon emissions and carbon emission intensity values of each province under the baseline scenario and the low-carbon scenario are predicted based on the STIRPAT model, which can limit the carbon emission dual control prediction to a relatively limited and dynamically changing range, improve the authenticity and reliability of carbon emissions and carbon emission intensity, and enhance the guiding significance of relevant research for provinces in formulating low-carbon development strategies. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 It is a schematic diagram of the steps of the carbon emission prediction method based on the STIRPAT model influencing factor development scenario analysis of the present invention; Figure 2 for Figure 1 Detailed step flow diagram of step S1; Figure 3 for Figure 1 Detailed step flow diagram of step S3; Figure 4 A structural diagram of a computing device of the present disclosure is presented. DETAILED DESCRIPTION
[0009] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0010] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0011] The present disclosure provides a carbon emission prediction method based on the STIRPAT model, comprising: obtaining data on influencing factors of carbon emissions and carbon emission intensity of each province, and performing data processing on the influencing factor data; using the ElasticNet method to screen the influencing factors of carbon emissions and carbon emission intensity of each province to obtain the initial screening results; constructing a model for the influencing factors of the initial screening to obtain an influencing factor analysis model based on the STIRPAT model; performing ridge regression analysis on the STIRPAT model to obtain the fitting coefficient of the model; Ridge regression was performed on the influencing factors to obtain the elasticity coefficients of the influencing factors of carbon emissions and carbon emission intensity in each province, and the predicted values of carbon emissions and carbon emission intensity in each province were obtained through the elasticity coefficients.
[0012] In the embodiments of the present invention, please refer to Figure 1 As shown, the specific steps include: Step S1: Use the decision tree method to fill in missing data values and obtain the panel data of influencing factors of each province; use the ElasticNet method to screen the influencing factors of carbon emissions and carbon emission intensity of each province to obtain the initial screening results.
[0013] The embodiment of the present invention first collects the annual China Energy Statistical Yearbook, China High-tech Industry Statistical Yearbook, Electric Power Industry Statistical Data Compilation and China Environmental Statistical Yearbook of each province, selects 19 influencing factors that may affect the carbon emission dual control indicators from the aspects of population, industrial production, economy, energy production and consumption, natural resources and environmental protection, and organizes the collected statistical data to ensure the integrity and accuracy of the data. Secondly, for the missing data values, the decision tree method is used to fill in and obtain the panel data of the influencing factors. Finally, the ElasticNet method is used to screen the influencing factors of carbon emissions and carbon emission intensity of each province respectively, and the initial screening results of the influencing factors are obtained.
[0014] Step S2: constructing a model for the influencing factors to obtain an influencing factor analysis model based on the STIRPAT model; Step S3: Perform ridge regression analysis on the STIRPAT model to obtain the model fitting coefficient and eliminate the multicollinearity between the influencing factors; perform ridge regression on the influencing factors to obtain the elasticity coefficients of the influencing factors of carbon emissions and carbon emission intensity in each province; The embodiment of the present invention uses ridge regression analysis to calculate the fitting coefficient of the STIRPAT model to eliminate the multicollinearity effects between influencing factors, selects data from 2002 to 2022 for each province, and performs ridge regression on the influencing factors obtained in step S1, thereby obtaining the elasticity coefficients of the influencing factors of carbon emissions and carbon emission intensity in each province.
[0015] Step S4: Conduct an empirical analysis on the factors affecting carbon emissions and carbon emission intensity of each province through the STIRPAT model to obtain the impact intensity of the factors affecting carbon emissions and carbon emission intensity of each province; Step S5: According to the scenario parameter settings of each province, the carbon emission dual control indicators for 2025 and 2030 are predicted through the STIRPAT model to obtain the predicted values of carbon emissions and carbon emission intensity of each province under the baseline scenario and low-carbon scenario.
[0016] The embodiment of the present invention calculates the predicted values of carbon emissions and carbon emission intensity of each province under the baseline scenario and low-carbon scenario in 2025 and 2030 through the STIRPAT model based on the influencing factors screened by the decision tree method and the ElasticNet method and the elasticity coefficient of the influencing factors obtained by ridge regression.
[0017] refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps: Step S11: Obtain influencing factors that may affect carbon emission dual control indicators from aspects such as population, industrial production, economy, energy production and consumption, natural resources and environmental protection; The embodiment of the present invention collects information from various provinces such as the China Energy Statistical Yearbook, the China High-tech Industry Statistical Yearbook, the Electric Power Industry Statistical Data Compilation, and the China Environment Statistical Yearbook, and selects 19 influencing factors that may affect the carbon emission dual control indicators from the aspects of population, industrial production, economy, energy production and consumption, natural resources and environmental protection, and organizes the collected statistical data to ensure the integrity and accuracy of the data.
[0018] Step S12: Using the decision tree method to fill missing values, predictive filling is performed based on data characteristics and data distribution to obtain panel data of influencing factors in each province; The embodiment of the present invention sorts out the collected data sets, supplements the missing parts, and uses the decision tree method to fill the missing values based on the data characteristics and data distribution, and finally obtains the panel data of the influencing factors of each province. In addition, the calculation formula for filling the missing values can also use any Step S13: using the ElasticNet method to screen the influencing factors of carbon emissions and carbon emission intensity of each province, and obtain the initial screening results of the influencing factors; Preferably, the screening calculation formula in step S13 is specifically: ; Where y is the output vector; X is the input feature matrix; is the feature weight vector; , is the regularization parameter. Control the weight ratio of L1 and L2 regularization, It is equivalent to L2 regularization. The optimization goal is to minimize the sum of the mean square error and the regularization term, where the weighted sum of the L1 regularization term and the L2 regularization term is given by control.
[0019] refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S3 in the embodiment, step S3 includes the following steps: Step S31: Perform ridge regression analysis on the STIRPAT model to obtain the model fitting coefficient and eliminate the multicollinearity between the influencing factors; The embodiment of the present invention selects 19 influencing factors that may affect the carbon emission dual control indicators from the aspects of population, industrial production, economy, energy production and consumption, natural resources and environmental protection by collecting the annual China Energy Statistical Yearbook, China High-tech Industry Statistical Yearbook, Power Industry Statistical Data Compilation and China Environment Statistical Yearbook of each province, and sorts out the collected statistical data to ensure the integrity and accuracy of the data. Due to the multicollinearity between the influencing factors, in order to eliminate this effect, ridge regression analysis is used to calculate the fitting coefficient of the STIRPAT model. Ridge regression analysis is a biased estimation regression method specifically used for collinear data analysis.
[0020] Step S32: Perform ridge regression on the influencing factors through SPSS PRO to obtain the elasticity coefficients of the influencing factors of carbon emissions and carbon emission intensity in each province; The embodiment of the present invention collects and organizes influencing factors by collecting information such as the China Energy Statistical Yearbook, China High-tech Industry Statistical Yearbook, Electric Power Industry Statistical Data Compilation, and China Environment Statistical Yearbook of each province over the years, and selects data from each province from 2002 to 2022. Ridge regression is performed on the influencing factors to obtain the elasticity coefficients of the influencing factors of carbon emissions and carbon emission intensity in each province.
[0021] Among them, the calculation formula for calculating the elastic coefficient using the STIRPAT model is as follows: ; Where: I represents carbon emissions, is the model coefficient; , , , They represent the factors affecting carbon emissions, namely The representative first-level indicator A is the population factor, which includes m second-level indicators, namely population size, urbanization level and family size; The representative first-level indicator B is the economic factor, including n second-level indicators, namely, GDP per capita, secondary industry structure, and agricultural economic development level; The representative first-level indicator C is the energy factor, which includes p second-level indicators, namely energy intensity, energy structure and electrification rate; The representative first-level indicator D is the technical factor, which includes q second-level indicators, namely, the education level, the level of scientific and technological innovation, and the degree of agricultural mechanization; is the error term of the model, reflecting the influence of other factors not included in the model. b, c, d, and e are the elasticity coefficients of each influencing factor, indicating the degree of influence of the independent variable on the dependent variable, that is, , , , (m=1,2,3, n=1,2,…,8, p=1,2,3, q=1,2,…,5) When the corresponding sub-factors change by 1%, the dependent variable will change by b%, c%, d% and e% accordingly.
[0022] The present invention firstly adopts the decision tree method to fill in the missing data values, obtains the panel data of the influencing factors of each province, and uses the ElasticNet method to screen the influencing factors of the carbon emissions and carbon emission intensity of each province, and obtains the initial screening results; secondly, the influencing factors are modeled to obtain the influencing factor analysis model based on the STIRPAT model; thirdly, the STIRPAT model is subjected to ridge regression analysis to obtain the fitting coefficient of the model, eliminate the multicollinearity relationship between the influencing factors, and the influencing factors are subjected to ridge regression to obtain the elasticity coefficients of the influencing factors of the carbon emissions and carbon emission intensity of each province; then, the influencing factors of the carbon emissions and carbon emission intensity of each province are empirically analyzed by the STIRPAT model to obtain the influence intensity of the influencing factors of the carbon emissions and carbon emission intensity of each province, thereby verifying the validity of the calculated elasticity coefficient; finally, according to the scenario parameter settings of each province, the carbon emissions and carbon emission intensity in 2025 and 2030 are predicted by the STIRPAT model to obtain the predicted values of the carbon emissions and carbon emission intensity of each province under the baseline scenario and the low-carbon scenario. The calculation of this forecasting method can limit the dual-control forecast of carbon emissions to a relatively limited and dynamically changing range, improve the authenticity and reliability of carbon emissions and carbon emission intensity, and provide support for provinces to formulate low-carbon development strategies.
[0023] Figure 4 is a structural diagram of the hardware architecture of a computing device provided by an embodiment of the present disclosure. Figure 3 As shown, the computing device 700 includes an input device 701, an input interface 702, a central processing unit 703, a memory 704, an output interface 705, and an output device 707. The input interface 702, the central processing unit 703, the memory 704, and the output interface 705 are connected to each other via a bus 710, and the input device 701 and the output device 706 are connected to the bus 710 via the input interface 702 and the output interface 705, respectively, and are further connected to other components of the computing device 700.
[0024] Figure 4 The computing device shown can also be implemented as a carbon emission prediction device based on the STIRPAT model, and the computing device may include: a processor and a memory storing computer executable instructions; when executing the computer executable instructions, the processor can implement the training method for carbon emission prediction based on the STIRPAT model provided in an embodiment of the present invention.
[0025] An embodiment of the present invention also provides a computer-readable storage medium, on which computer program instructions are stored; when the computer program instructions are executed by a processor, the training method of the photovoltaic power generation prediction model provided by the embodiment of the present invention is implemented, or the photovoltaic power generation power prediction method provided by the embodiment of the present invention is implemented.
[0026] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.
[0027] The functional blocks shown in the structural block diagram described above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link through a data signal carried in a carrier. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memories (ROM), flash memory, erasable read-only memories (EROM), floppy disks, compact disc read-only memories (CD-ROM), optical discs, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segments can be downloaded via computer networks such as the Internet, intranets, etc.
[0028] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.
[0029] Aspects of the present disclosure are described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.
[0030] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.
Claims
1. The carbon emission prediction method based on the STIRPAT model is characterized by: include: Obtain data on factors affecting carbon emissions and carbon emission intensity in each province, and process the data on factors affecting carbon emissions; The ElasticNet method was used to screen the factors affecting the carbon emissions and carbon emission intensity of each province, and the initial screening results were obtained; The model of influencing factors of the initial screening was constructed to obtain an influencing factor analysis model based on the STIRPAT model; Ridge regression analysis was performed on the STIRPAT model to obtain the model fitting coefficients; Ridge regression was performed on the influencing factors to obtain the elasticity coefficients of the influencing factors of carbon emissions and carbon emission intensity in each province, and the predicted values of carbon emissions and carbon emission intensity in each province were obtained through the elasticity coefficients.
2. The carbon emission prediction method based on the STIRPAT model according to claim 1 is characterized in that: The coal-electricity chain carbon emission measurement model is as follows: the influencing factor data is processed, including data filling, and the data filling adopts a decision tree method to fill in missing data values.
3. The carbon emission prediction method based on the STIRPAT model according to claim 2 is characterized in that: The ElasticNet method is used to screen the factors affecting the carbon emissions and carbon emission intensity of each province to obtain the initial screening results. The specific formula used is as follows: In the formula, y is the output vector, X is the input feature matrix, is the feature weight vector, , is the regularization parameter, Represents the weight ratio of controlling L1 and L2 regularization.
4. The carbon emission prediction method based on the STIRPAT model according to claim 1 or 3, characterized in that: The STIRPAT model is specifically: ； In the formula, I represents carbon emissions; is the model coefficient; , , , They represent the influencing factors of different indicators of carbon emissions; represents the error term of the model.
5. The carbon emission prediction method based on the STIRPAT model according to claim 4 is characterized in that: The ridge regression is performed on the influencing factors to obtain the elasticity coefficients of the influencing factors of carbon emissions and carbon emission intensity in each province, where the calculation formula of the elasticity coefficient is as follows: 。 6. A carbon emission prediction device based on the STIRPAT model, characterized in that: include: The data acquisition module is used to obtain the data on influencing factors of carbon emissions and carbon emission intensity in each province, and to process the data on influencing factors; The screening module is used to screen the factors affecting the carbon emissions and carbon emission intensity of each province using the ElasticNet method to obtain the initial screening results; The model building module is used to build a model for the influencing factors of the initial screening and obtain an influencing factor analysis model based on the STIRPAT model; Model analysis module, used to perform ridge regression analysis on the STIRPAT model and obtain the model fitting coefficients; The prediction module is used to perform ridge regression on the influencing factors to obtain the elasticity coefficients of the influencing factors of carbon emissions and carbon emission intensity in each province, and to predict the carbon emissions and carbon emission intensity of each province through the elasticity coefficients.
7. An electronic device, characterized in that: It includes a processor, and a memory and a network interface connected to the processor; the network interface is connected to a non-volatile memory in a server; when the processor is running, it calls a computer program from the non-volatile memory through the network interface, and runs the computer program through the memory to execute the method described in any one of claims 1 to 5.
8. A storage medium, characterized in that: The computer storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 5 is implemented.