A prediction method and system for urban carbon peak time domain

Abstract

The present invention discloses a method and system for predicting the time domain of urban carbon peak, wherein the method includes: S1: obtaining multiple characteristic factors that affect the urban carbon peak and building a hierarchical analysis framework for urban carbon emission prediction; S2: using the hierarchical analysis framework to screen the principal component factors and obtain historical observation data; S3: based on the historical observation data of the principal component factors, using the Pearson correlation coefficient to quantitatively characterize the relationship between the explanatory variables and the predictive variables, testing the significance of the correlation between the observed data and the predictive variables, and fitting the regression prediction relationship of the urban carbon emissions; S4: calculating the trend fitting data value of the explanatory variable, using the regression prediction relationship to predict the prediction interval of the urban carbon emissions within a predetermined time, finding the carbon peak according to the prediction interval, and performing a prediction analysis of the urban carbon peak time domain. The present invention can provide theoretical support through the prediction analysis of urban carbon emissions, thereby better carrying out subsequent decision-making and management.

Description

Technical Field

[0001] The present invention relates to the field of carbon emission analysis, and in particular to a method and system for predicting the time domain of urban carbon peak. Background Art

[0002] Climate change is a common issue facing humanity worldwide. Carbon emissions are considered a key indicator of climate change, and therefore carbon peaking is a key goal. Carbon peaking refers to the point in time when a city's carbon dioxide emissions cease to increase, reaching a peak and then gradually declining, marking the decoupling of carbon emissions from economic development.

[0003] Currently, most patents for carbon emission forecasting focus on specific entities or systems, with few addressing macro-level carbon emission forecasts for cities. Cities in eastern my country, as part of the country's more developed regions, emit significant amounts of carbon. The magnitude of these emissions directly impacts whether the "carbon peak" target can be achieved on schedule. Currently available data cannot predict carbon peaks for cities, thus failing to provide theoretical support for subsequent decision-making. Summary of the Invention

[0004] Based on the problems arising in the background technology, the embodiments of the present application provide a method and system for predicting the time domain of urban carbon peak. According to energy data statistics, the technical solution of the present application can be used to predict the time domain of urban carbon peak, thereby providing theoretical support for relevant decision-making and formulating better policies.

[0005] In a first aspect, an embodiment of the present application provides a method for predicting the time domain of a city's carbon peak, the method comprising:

[0006] S1: Based on the two-dimensional temporal evolution of urban carbon emissions, we obtain multiple characteristic factors that affect urban carbon peaking and use these characteristic factors to build a hierarchical analysis framework for urban carbon emissions prediction.

[0007] S2: Using the analytic hierarchy process framework, filter out the principal component factors that affect urban carbon emissions from the multiple characteristic factors, and obtain historical observation data of the principal component factors;

[0008] S3: Based on the historical observation data of the principal component factors, the Pearson correlation coefficient is used to quantitatively characterize the relationship between the explanatory variables and the predictor variables, the significance of the correlation between the observation data and the predictor variables is tested, and a regression prediction relationship of urban carbon emissions is fitted based on the variable data;

[0009] S4: Trend fit the changing trend of the principal component factor data, calculate the trend fitting data value of the explanatory variable, use the regression prediction relationship to predict the prediction interval of the city's carbon emissions within a predetermined time, find the carbon peak according to the prediction interval, and conduct a prediction analysis of the city's carbon peak time domain.

[0010] Furthermore, in the step S1, before building the urban carbon emission prediction network architecture, the step further includes: performing index grading detection on the characteristic factors using a preset logical self-consistent index system, so as to set the characteristic factors in the prediction network architecture in a hierarchical manner;

[0011] Among them, in the logically self-consistent indicator system, the first-level indicators are set according to construction consumption and transformation optimization, the secondary indicators are set according to energy-driven consumption, urban development consumption, and green transformation optimization, and the third-level indicators are set according to energy structure, energy consumption, energy consumption scale, urbanization rate, population density, economic level, green industry ratio, energy structure optimization, and energy utilization efficiency.

[0012] Furthermore, in the step S2, after the principal component factors are screened out, the step further includes establishing time domain scale data of the principal component factors, and using the time domain scale data to clean the historical observation data to achieve data optimization.

[0013] Furthermore, the time-domain scale data includes geographical distribution data and time-ordered data, and a unified standard caliber is used to implement data cleaning to achieve horizontal accuracy of the control data.

[0014] Furthermore, in step S3, it further includes: using the relationship (1) to perform product difference, calculating the deviation of the two variables from their respective average values, and obtaining the principal component factor and the correlation coefficient γ of the urban carbon emissions by multiplying the two deviations.

[0015]

[0016] Based on the large data sample space of explanatory variables and predictor variables, the significance of the correlation between historical observation data and predictor variables is tested by t test. Using the relationship (2), the test statistic t obeys the t distribution with n-2 degrees of freedom.

[0017]

[0018] Among them, r is the correlation coefficient; t is the test statistic; n is the sample size of the statistical data; x is the observed value of the factor statistic; and y is the statistical value of the city's carbon emissions over the years.

[0019] Furthermore, the method of deriving the regression prediction relationship of urban carbon emissions based on the nonlinear fitting equation of variable data includes: according to the principle of least squares method, nonlinearly fitting the mathematical expressions (3), (4), and (5) between the variable data to derive the regression prediction relationship of urban carbon emissions;

[0020]

[0021]

[0022]

[0023] in, is the regression parameter; is the observed mean of the explanatory variable; is a predictor variable for the city’s future carbon emissions.

[0024] Furthermore, before step S4, the method further includes: testing the credibility of the regression prediction relationship of urban carbon emissions, calculating the goodness of fit of the regression prediction relationship between variables, obtaining the linear influence of the principal component factors on the prediction variables, and the nonlinear influence of other factors on the prediction variables.

[0025] Furthermore, the method for calculating the goodness of fit of the regression prediction relationship between variables is to use the variance analysis of the predictive variables using formula (6) and calculate the determination coefficient to explain the goodness of fit of the regression mathematical equation between variables:

[0026]

[0027] Among them, SST is the total variance sum of squares, SSR is the regression variance sum of squares, SSE is the residual sum of squares, r is the correlation coefficient, and r1 is the determination coefficient.

[0028] Formula (7) is used to calculate the standard error to explain the nonlinear effects of other factors on the research object;

[0029]

[0030] Furthermore, in step S4, the trend of the principal component factor data is fitted using formula (8), and the data value is fitted according to the trend of the explanatory variable, and the prediction interval of the urban carbon emissions is predicted by the regression prediction relationship.

[0031]

[0032] in, is the predictor variable of the explanatory variable x0, x0 is the future carbon emissions of the corresponding city; α / 2 (n-2) is the lateral parameter value of the t distribution statistic.

[0033] In a second aspect, an embodiment of the present application provides a city carbon peak time-domain regression prediction system, using any method described in the first aspect, the system comprising:

[0034] A framework building module is configured to obtain multiple characteristic factors that affect urban carbon peak based on the two-dimensional evolution behavior of urban carbon emissions in the time domain, and use the characteristic factors to build a hierarchical analysis framework for urban carbon emissions prediction;

[0035] a data screening module configured to use the hierarchical analysis framework to screen out the main component factors affecting urban carbon emissions from the plurality of characteristic factors, and obtain historical observation data of the main component factors;

[0036] a relationship determination module configured to quantitatively characterize the relationship between the explanatory variable and the predictor variable using the Pearson correlation coefficient based on the historical observation data of the principal component factors, test the significance of the correlation between the observation data and the predictor variable, and fit a regression prediction relationship for urban carbon emissions based on the variable data;

[0037] The prediction and analysis module is configured to trend fit the changing trend of the principal component factor data, calculate the trend fitting data value of the explanatory variable, use the regression prediction relationship to predict the prediction interval of the city's carbon emissions within a predetermined time, find the carbon peak based on the prediction interval, and conduct a prediction analysis of the city's carbon peak time domain.

[0038] The technical solutions provided in the embodiments of this application have at least the following technical effects:

[0039] By adopting the regression prediction of the city's future carbon emissions, we can obtain the predicted range of the city's carbon emissions in the next N years. By providing a scientific and reliable low-carbon energy transformation and smart city carbon peak time domain prediction solution, we can provide theoretical support for relevant departments and policies, and better carry out subsequent policy formulation and work management. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flowchart of the time-domain regression prediction method for urban carbon peak in Example 1 of this application;

[0041] Figure 2 This is the hierarchical analysis framework in Example 1 of this application;

[0042] Figure 3 This is the carbon emission prediction trend curve in Example 1 of this application;

[0043] Figure 4 This is a module diagram of the urban carbon peak time-domain regression prediction system in Example 2 of this application. DETAILED DESCRIPTION

[0044] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0045] Before elaborating on the technical solution of this embodiment, it is supplemented that this embodiment is used for the carbon peak time domain prediction when transforming smart cities into low-carbon energy cities in the east, such as Shanghai. Specifically, taking urban carbon emissions as the research object, the characteristic factors affecting urban carbon emissions are comprehensively considered in all aspects. The characteristic factors include energy-driven consumption (energy structure, total energy consumption, energy consumption scale), urban development consumption (urbanization rate, population density, economic level), and green sustainable transformation (green industry ratio, energy utilization efficiency, energy structure optimization). Taking Shanghai as an example, energy consumption is selected as a macro-statistic. The following is Table 1 for energy consumption and urban carbon emissions from 2000 to 2020.

[0046] Table 1 Data on total energy consumption and urban carbon emissions in Shanghai from 2000 to 2020

[0047] years Total energy consumption (10,000 tons of standard coal) Urban carbon emissions (10,000 tC) 2000 5413.45 3627.14 2001 5825.8 3959.43 2002 6114.47 4143.25 2003 6658.49 4405.01 2004 7176.16 4638.47 2005 7730.66 4862.38 2006 8355.49 5164.79 2007 9103.3 5917.41 2008 9608.49 6053.83 2009 9759.35 6245.98 2010 10243.26 6248.39 2011 10489.09 6713.01 2012 10573 6660.99 2013 10890.39 7024.30 2014 10639.86 6862.71 2015 10930.53 6667.62 2016 11241.73 6834.97 2017 11381.85 6851.87 2018 11453.73 6883.69 2019 11696.49 6936 2020 11099.59 6582.05

[0048] Example 1

[0049] Reference Attachment Figure 1 As shown, an embodiment of the present application provides a time-domain regression prediction method for urban carbon peak, which includes the following steps.

[0050] Step S1: Based on the two-dimensional evolution behavior of urban carbon emissions in the time domain, obtain multiple characteristic factors that affect the urban carbon peak, and use the characteristic factors to build a city carbon emission prediction model. Figure 2 The hierarchical analysis framework shown.

[0051] In step S1, before building the urban carbon emission prediction network architecture, it also includes: using a preset logical self-consistent index system to perform index classification detection on the characteristic factors, so as to set the characteristic factors in the prediction network architecture according to the hierarchy.

[0052] Among them, in the logically self-consistent indicator system, the first-level indicators are set according to construction consumption and transformation optimization, the secondary indicators are set according to energy-driven consumption, urban development consumption, and green transformation optimization, and the third-level indicators are set according to energy structure, energy consumption, energy consumption scale, urbanization rate, population density, economic level, green industry ratio, energy structure optimization, and energy utilization efficiency.

[0053] It can be seen from this that in analyzing the all-round factors affecting carbon emissions in the eastern region's smart city transformation, with economic theory as the core and empirical research as the extension, we establish first-level indicators of construction consumption and transformation optimization, secondary indicators of energy-driven consumption, urban development consumption, and green transformation optimization, and third-level indicators of energy structure, energy consumption, energy consumption scale, urbanization rate, population density, economic level, green industry ratio, energy structure optimization, and energy utilization efficiency, forming a logically self-consistent indicator system.

[0054] The specific impact mechanisms of indicators at each level are described as follows:

[0055] Since energy consumption is the primary source of greenhouse gas emissions, greenhouse gas emissions have long been determined by economic structure. As the world's largest developing country, my country's rapid economic development requires significant energy consumption, generating greenhouse gases and leading to significant total carbon emissions. Therefore, energy consumption needs to be considered. Scientific and technological advances can improve energy efficiency, thereby slowing or even reducing carbon dioxide emissions. Energy efficiency is also a factor. Greening traditional industries through the use of low-harm or harmless technologies reduces resource or energy consumption, thereby achieving low pollution. Increasing the proportion of green industries can effectively curb carbon emissions, thus contributing to the need for consideration.

[0056] In this example, in order to predict the carbon peak time domain of Shanghai, Shanghai's carbon emissions are taken as the research object, and the factors affecting urban carbon emissions are comprehensively considered. Energy-driven consumption (energy structure, total energy consumption, energy consumption scale), urban development consumption (urbanization rate, population density, economic level), and green sustainable transformation (green industry ratio, energy utilization efficiency, energy structure optimization) are selected as the main factors affecting carbon emissions. A pre-analysis framework for the comprehensive evaluation of urban carbon emissions is constructed. Figure 1 The hierarchical analysis framework shown.

[0057] Step S2: Utilizing the analytic hierarchy process framework, the principal component factors influencing urban carbon emissions are screened out from the plurality of characteristic factors, and historical observation data of the principal component factors are obtained.

[0058] In the step S2, after the principal component factors are screened out, the method further includes establishing time domain scale data of the principal component factors, and using the time domain scale data to clean the historical observation data to achieve data optimization.

[0059] The time-domain scale data includes geographical distribution data and time-ordered data, and a unified standard caliber is used to implement data cleaning to achieve the horizontal accuracy of the control data.

[0060] Based on the evaluation system and hierarchical analysis framework of urban carbon emissions, for example, the selected characteristic factors include: energy structure, total energy consumption, energy consumption scale, urbanization rate, population density, economic level, green industry ratio, energy utilization efficiency, and energy structure optimization. Among them, total energy consumption is used as a macro statistic, and the changes in carbon emissions of specific cities are predicted through explanatory variables.

[0061] For example, the data of Shanghai's energy consumption and urban carbon emissions from 2000 to 2020 are used to calculate X. 2 、Y 2 , XY related statistical function data, see Table 2. Figure 3 As shown in the figure, Shanghai's carbon emission forecast trend curve.

[0062] Table 2 Data on total energy consumption, urban carbon emissions and related quantities in Shanghai from 2000 to 2020

[0063]

[0064] Step S3: Based on the historical observation data of the principal component factors, the Pearson correlation coefficient is used to quantitatively characterize the relationship between the explanatory variables and the predictor variables, the significance of the correlation between the observation data and the predictor variables is tested, and a regression prediction relationship of urban carbon emissions is fitted based on the variable data.

[0065] In step S3, it further includes: using the relationship (1) to perform product difference, calculating the deviation of the two variables from their respective average values, and obtaining the principal component factor and the correlation coefficient γ of the urban carbon emissions by multiplying the two deviations.

[0066]

[0067] According to the large data sample space of explanatory variables and predictor variables, the significance of the correlation between historical observation data and predictor variables is tested by t test. Using the relationship (2), the test statistic t obeys the t distribution with n-2 degrees of freedom.

[0068]

[0069] Among them, r is the correlation coefficient; t is the test statistic; n is the sample size of the statistical data; x is the observed value of the factor statistic; and y is the statistical value of the city's carbon emissions over the years.

[0070] In this embodiment, the significance test of the overall data is performed according to the significance level α=0.05, specifically:

[0071]

[0072] Optionally, the data in the table are substituted into the formula to calculate the correlation coefficient between the factor statistics and the city's carbon emissions, and perform a significance test on the correlation coefficient.

[0073] Correlation coefficient:

[0074] Perform significance test on the correlation coefficient and calculate the test statistic:

[0075]

[0076] The significance level is set to α = 0.05, as shown in Table 3. According to the t-distribution statistic, we can obtain:

[0077] Table 3 Statistical t distribution lateral parameter values

[0078] Alpha 0.1 0.05 0.025 0.01 1 3.078 6.314 12.706 31.821 2 1.886 2.92 4.303 6.965 3 1.638 2.353 3.182 4.541 4 1.533 2.132 2.776 3.747 5 1.476 2.015 2.571 3.365 6 1.44 1.943 2.447 3.143 7 1.415 1.895 2.365 2.998 8 1.397 1.86 2.306 2.998 ... ... ... ... ... 19 1.328 1.729 2.093 2.539

[0079] t α / 2 (n-2)=t 0.025 (21-2)=2.093, t=30.5725>tα / 2(21-2)=2.093, so the correlation between Shanghai's total energy consumption and urban carbon emissions from 2010 to 2020 is significant.

[0080] According to the principle of least squares method, the mathematical expressions (3), (4), and (5) between the nonlinear fitting variable data are used to derive the regression prediction relationship of urban carbon emissions. The formula used is:

[0081]

[0082]

[0083]

[0084] in, is the regression parameter; is the observed mean of the explanatory variable; is a predictor variable for the city's future carbon emissions. In one embodiment, it can be understood as the future carbon emissions of smart cities in the eastern region during the low-carbon energy transition. Thus, taking Shanghai as an example, the regression prediction relationship between Shanghai's total energy consumption and urban carbon emissions is recursively derived:

[0085]

[0086]

[0087]

[0088] From the regression prediction relationship between total energy consumption and urban carbon emissions in Shanghai, it can be seen that for every 10,000 tons of standard coal increase in average energy consumption, annual carbon emissions will increase by 7,500 tons of C.

[0089] Step S4: Trend fit the changing trend of the principal component factor data, calculate the trend fitting data value of the explanatory variable, use the regression prediction relationship to predict the prediction interval of the city's carbon emissions within a predetermined time, find the carbon peak according to the prediction interval, and conduct a prediction analysis of the city's carbon peak time domain.

[0090] Before step S4, the method also includes: testing the credibility of the regression prediction relationship of urban carbon emissions, calculating the goodness of fit of the regression prediction relationship between variables, obtaining the linear influence of the principal component factors on the prediction variables, and the nonlinear influence of other factors on the prediction variables.

[0091] In actual operation, the linear influence of the principal component factors on the predicted variables can be eliminated first, and then the nonlinear influence of other factors on the predicted variables can be processed.

[0092] Specifically, the method for calculating the goodness of fit of the regression prediction relationship between variables is: using the variance analysis of the predictor variables using formula (6), and calculating the determination coefficient to explain the goodness of fit of the regression mathematical equation between variables:

[0093]

[0094] Among them, SST is the total variance sum of squares, SSR is the regression variance sum of squares, SSE is the residual sum of squares, r is the correlation coefficient, and r1 is the determination coefficient.

[0095] Furthermore, the coefficient of determination is calculated to explain the goodness of fit of the regression prediction relationship between variables.

[0096] r 2 =0.989 2 =0.980

[0097] The coefficient of determination shows that 98% of changes in urban carbon emissions are determined by total energy consumption. There is a strong linear correlation between total energy consumption and urban carbon emissions, and the regression prediction equation has a high goodness of fit. This regression prediction model accurately predicts total energy consumption and urban carbon emissions.

[0098] Specifically, formula (7) is used to calculate the standard error to explain the nonlinear effects of other factors on the research object;

[0099]

[0100] In one embodiment, the standard error is calculated to account for the nonlinear effects of other factors on the study object:

[0101]

[0102] It can be seen from the standard error that when predicting urban carbon emissions based on total urban energy consumption, the nonlinear impact of other factors on urban carbon emissions is 165.1, that is, the average error of the carbon emission prediction model is 1.651 million tC.

[0103] In step S4, the trend of the principal component factor data is fitted using formula (8), and the data value is fitted according to the trend of the explanatory variable, and the prediction interval of the urban carbon emissions is predicted through the regression prediction relationship;

[0104]

[0105] in, is the predictor variable of the explanatory variable x0, x0 is the future carbon emissions of the corresponding city; α / 2 (n-2) is the lateral parameter value of the t distribution statistic.

[0106] Based on the trend of the observed values ​​of the selected factors, the predicted values ​​of the future dependent variables are determined, and the total energy consumption and carbon emissions of specific cities in the next few years are predicted through regression prediction relationships.

[0107] Based on the data of Shanghai’s total energy consumption and urban carbon emissions from 2000 to 2020, the trend changes were fitted nonlinearly (y = -18.162x2 + 715.18x + 4348.2, where x is the corresponding sequence number “1, 2, …”), and the future urban carbon emissions from 2021 to 2040 were obtained, as shown in Table 4.

[0108] Table 4 Fitting values ​​of Shanghai’s total energy consumption and urban carbon emissions from 2022 to 2040

[0109]

[0110] Since other factors have nonlinear effects on the predicted variables after excluding the linear effects of the principal component factors on the predicted variables, the total carbon emissions obtained by simply relying on the regression prediction relationship of the eastern transformation smart city carbon emissions is not an accurate result. In order to improve the prediction accuracy, it is necessary to give a reliable interval of the predicted value of urban carbon emissions based on the predicted value.

[0111] Therefore, the average total energy consumption from 2020 to 2025 is substituted into formulas (5) and (8) to calculate the confidence intervals of the predicted total carbon emissions of smart cities in the eastern region and the predicted urban carbon emissions, respectively, as shown in Table 5 (confidence level is α = 0.05).

[0112] Table 5. Confidence intervals for the predicted carbon emissions of Shanghai in that year

[0113]

[0114]

[0115] As shown in Table 5, in the next six years, as energy consumption increases during urban construction, urban carbon emissions will also increase. The confidence intervals for urban carbon emissions in the next few years are given. The carbon emission forecast trend curve and carbon peak chart for smart cities in the eastern region, represented by Shanghai, are detailed in Table 5. Figure 2 . When the total urban energy consumption in 2027 is 104.17962 million tons of standard coal, the amplitude of Shanghai's carbon emission forecast trend curve is (84.70432, 77.58218) million tons of standard coal, and the confidence interval of the city's total carbon emissions is (84.70432, 77.58218) million tons of C. Shanghai will reach its carbon peak in the future and achieve the predicted time point of decoupling economic development and carbon emissions. The present invention realizes the forecast analysis of carbon emissions of smart cities in the eastern transformation represented by Shanghai, provides theoretical support for government departments, key energy-consuming units, enterprises, etc., and better carries out the next step of policy formulation and management.

[0116] Example 2

[0117] An embodiment of the present application provides a city carbon peak time-domain regression prediction system, which adopts the method described in any one of Example 1, and the system includes the following modules.

[0118] The framework building module 100 is configured to obtain multiple characteristic factors that affect the city's carbon peak based on the two-dimensional temporal evolution of the city's carbon emissions, and use the characteristic factors to build a hierarchical analysis framework for urban carbon emissions prediction;

[0119] The data screening module 200 is configured to use the hierarchical analysis framework to screen out the main component factors that affect urban carbon emissions from the multiple characteristic factors, and obtain historical observation data of the main component factors;

[0120] The relationship determination module 300 is configured to quantitatively characterize the relationship between the explanatory variable and the predictor variable using the Pearson correlation coefficient based on the historical observation data of the principal component factors, test the significance of the correlation between the observation data and the predictor variable, and fit a regression prediction relationship for urban carbon emissions based on the variable data;

[0121] The prediction and analysis module 400 is configured to trend fit the changing trend of the principal component factor data, calculate the trend fitting data value of the explanatory variable, use the regression prediction relationship to predict the prediction interval of the city's carbon emissions within a predetermined time, and find the carbon peak based on the prediction interval to realize the prediction analysis of the city's carbon peak time domain.

[0122] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0124] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0125] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0126] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0127] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for predicting the time domain of urban carbon peak, characterized in that: The method comprises: S1: Based on the two-dimensional temporal evolution of urban carbon emissions, we obtain multiple characteristic factors that affect urban carbon peaking and use these characteristic factors to build a hierarchical analysis framework for urban carbon emissions prediction. S2: Using the analytic hierarchy process framework, filter out the principal component factors that affect urban carbon emissions from the multiple characteristic factors, and obtain historical observation data of the principal component factors; S3: Based on the historical observation data of the principal component factors, the Pearson correlation coefficient is used to quantitatively characterize the relationship between the explanatory variables and the predictor variables, the significance of the correlation between the observation data and the predictor variables is tested, and a regression prediction relationship of urban carbon emissions is fitted based on the variable data; S4: Trend fitting the changing trend of the principal component factor data, calculating the trend fitting data value of the explanatory variable, using the regression prediction relationship to predict the prediction interval of the city's carbon emissions within a predetermined time, and finding the carbon peak according to the prediction interval to perform a prediction analysis of the city's carbon peak time domain; Among them, step S3 further includes: using the relationship (1) to perform product difference, calculating the deviation of the two variables from their respective average values, and obtaining the principal component factor and the correlation coefficient of urban carbon emissions by multiplying the two deviations. ; ……（1） According to the large data sample space of explanatory variables and predictor variables, the significance of the correlation between historical observation data and predictor variables is tested by t test. Using the relationship (2), the test statistic t obeys the t distribution with n-2 degrees of freedom. ……（2） Among them, r is the correlation coefficient; t is the test statistic; n is the sample size of the statistical data; x is the observed value of the factor statistic; y is the statistical value of the city's carbon emissions over the years; The method of deriving the regression prediction relationship of urban carbon emissions based on the nonlinear fitting equation of variable data includes: according to the principle of least squares method, nonlinearly fitting the mathematical expressions (3), (4), (5) between the variable data to derive the regression prediction relationship of urban carbon emissions; ……（3） ……（4） ……（5） in, is the regression parameter; is the observed mean of the explanatory variable; is a predictor variable for the city’s future carbon emissions.

2. The method for predicting the urban carbon peak time domain according to claim 1 is characterized in that: In the step S1, before building the urban carbon emission prediction network architecture, the method further includes: performing index grading detection on the characteristic factors using a preset logical self-consistent index system, so as to set the characteristic factors in layers in the prediction network architecture; Among them, in the logically self-consistent indicator system, the first-level indicators are set according to construction consumption and transformation optimization, the secondary indicators are set according to energy-driven consumption, urban development consumption, and green transformation optimization, and the third-level indicators are set according to energy structure, energy consumption, energy consumption scale, urbanization rate, population density, economic level, green industry ratio, energy structure optimization, and energy utilization efficiency.

3. The method for predicting the urban carbon peak time domain according to claim 1 is characterized in that: In the step S2, after the principal component factors are screened out, the step further includes establishing time domain scale data of the principal component factors, and using the time domain scale data to clean the historical observation data to achieve data optimization.

4. The method for predicting the urban carbon peak time domain according to claim 2 is characterized in that: The time-domain scale data includes geographical distribution data and time-ordered data, and unifies the standard caliber to achieve data cleaning to achieve the horizontal accuracy of the control data.

5. The method for predicting the urban carbon peak time domain according to claim 1 is characterized in that: Before step S4, the method also includes: testing the credibility of the regression prediction relationship of urban carbon emissions, calculating the goodness of fit of the regression prediction relationship between variables, obtaining the linear influence of the principal component factors on the prediction variables, and the nonlinear influence of other factors on the prediction variables.

6. The method for predicting the urban carbon peak time domain according to claim 5 is characterized in that: The method for calculating the goodness of fit of the regression prediction relationship between variables is: The variance analysis of the predictor variables using formula (6) was used to calculate the coefficient of determination to explain the goodness of fit of the regression mathematical equation between the variables: ……（6）； Among them, SST is the total variance sum of squares, SSR is the regression variance sum of squares, SSE is the residual sum of squares, r is the correlation coefficient, is the coefficient of determination; Formula (7) is used to calculate the standard error to explain the nonlinear effects of other factors on the research object; ……（7）。 7. The method for predicting the urban carbon peak time domain according to claim 1 is characterized in that: In step S4, the trend of the principal component factor data is fitted using formula (8), and the data value is fitted according to the trend of the explanatory variable, and the prediction interval of the urban carbon emissions is predicted by the regression prediction relationship. ……（8）； in, is the explanatory variable The predictor variables, To correspond to the city’s future carbon emissions; is the lateral parameter value of the t-distribution statistic.

8. A city carbon peak time domain prediction system, using the method according to any one of claims 1 to 7, characterized in that: The system comprises: A framework building module is configured to obtain multiple characteristic factors that affect urban carbon peak based on the two-dimensional evolution behavior of urban carbon emissions in the time domain, and use the characteristic factors to build a hierarchical analysis framework for urban carbon emissions prediction; a data screening module configured to use the hierarchical analysis framework to screen out the main component factors affecting urban carbon emissions from the plurality of characteristic factors, and obtain historical observation data of the main component factors; a relationship determination module configured to quantitatively characterize the relationship between the explanatory variable and the predictor variable using the Pearson correlation coefficient based on the historical observation data of the principal component factors, test the significance of the correlation between the observation data and the predictor variable, and fit a regression prediction relationship for urban carbon emissions based on the variable data; The prediction and analysis module is configured to trend fit the changing trend of the principal component factor data, calculate the trend fitting data value of the explanatory variable, use the regression prediction relationship to predict the prediction interval of the city's carbon emissions within a predetermined time, find the carbon peak based on the prediction interval, and conduct a prediction analysis of the city's carbon peak time domain.

Images