Browse > Article
http://dx.doi.org/10.4491/eer.2016.153

Prediction of carbon dioxide emissions based on principal component analysis with regularized extreme learning machine: The case of China  

Sun, Wei (Department of Business Administration, North China Electric Power University)
Sun, Jingyi (Department of Business Administration, North China Electric Power University)
Publication Information
Environmental Engineering Research / v.22, no.3, 2017 , pp. 302-311 More about this Journal
Abstract
Nowadays, with the burgeoning development of economy, $CO_2$ emissions increase rapidly in China. It has become a common concern to seek effective methods to forecast $CO_2$ emissions and put forward the targeted reduction measures. This paper proposes a novel hybrid model combined principal component analysis (PCA) with regularized extreme learning machine (RELM) to make $CO_2$ emissions prediction based on the data from 1978 to 2014 in China. First eleven variables are selected on the basis of Pearson coefficient test. Partial autocorrelation function (PACF) is utilized to determine the lag phases of historical $CO_2$ emissions so as to improve the rationality of input selection. Then PCA is employed to reduce the dimensionality of the influential factors. Finally RELM is applied to forecast $CO_2$ emissions. According to the modeling results, the proposed model outperforms a single RELM model, extreme learning machine (ELM), back propagation neural network (BPNN), GM(1,1) and Logistic model in terms of errors. Moreover, it can be clearly seen that ELM-based approaches save more computing time than BPNN. Therefore the developed model is a promising technique in terms of forecasting accuracy and computing efficiency for $CO_2$ emission prediction.
Keywords
$CO_2$ emissions prediction; Influential factors; PACF; PCA; Pearson coefficient test; RELM;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Azadeh A, Tarverdian S. Integration of genetic algorithm, computer simulation and design of experiments for forecasting electrical energy consumption. Energ. Policy 2007;35:5229-5241.   DOI
2 Utgikar PV, Scott PJ. Energy forecasting: Predictions, reality and analysis of cause of error. Energ. Policy 2006;34:3087-3092.   DOI
3 Aydin G. The development and validation of regression models to predict energy-related $CO_2$ emissions in Turkey. Energ. Source. Part B. 2016;10:176-182.
4 Aydin G. The modeling of coal-related $CO_2$ emissions and projections into future planning. Energ. Source. Part A. 2014;36: 191-201.   DOI
5 Feng YY, Zhang LX. Scenario analysis of urban energy saving and carbon abatement policies: A case study of Beijing city, China. Procedia Environ. Sci. 2012;13:632-644.   DOI
6 Lin BQ, Moubarak M. Decomposition analysis: Change of carbon dioxide emissions in the Chinese textile industry. Renew. Sust. Energ. Rev. 2013;26:389-396.   DOI
7 Gonzalez PF, Landajo M, Presno MJ. The driving forces behind changes in $CO_2$ emission levels in EU-27. Differences between member states. Environ. Sci. Policy 2013;38:11-16.
8 Zhang Y, Wang HK, Liang S, et al. Temporal and spatial variations in consumption-based carbon dioxide emissions in China. Renew. Sust. Energ. Rev. 2014;40:60-68.   DOI
9 Wang YF, Zhao HY, Li LY, et al. Carbon dioxide emission drivers for a typical metropolis using input-output structural decomposition analysis. Energ. Policy 2013;58:312-318.   DOI
10 Andres AR, Rustemoglu H. Determinants of $CO_2$ emissions in Brazil and Russia between 1992 and 2011: A decomposition analysis. Environ. Sci. Policy 2016;58:95-106.   DOI
11 Deng MX, Li W, Hu Y. Decomposing industrial energy-related $CO_2$ emissions in Yunnan Province, China: Switching to low-carbon economic growth. Energies 2016;9:23.   DOI
12 Li Q, Wei YN, Dong YF. Coupling analysis of China's urbanization and carbon emissions: example from Hubei Province. Nat. Hazards 2016;81:1333-1348.   DOI
13 Li W, Ou Q, Chen Y. Decomposition of China's $CO_2$ emissions from agriculture utilizing an improved Kaya identity. Environ. Sci. Pollut. Res. 2014;21:13000-13006.   DOI
14 Wang QW, Chiu YH, Chiu CR. Driving factors behind carbon dioxide emissions in China: A modified production-theoretical decomposition analysis. Energ. Econ. 2015;51:252-260.   DOI
15 Ahmed K. The sheer scale of China's urban renewal and $CO_2$ emissions: multiple structural breaks, long-run relationship, and short-run dynamics. Environ. Sci. Pollut. Res. 2016;23: 16115-16126.   DOI
16 Ali HS, Law SH, Zannah TI. Dynamic impact of urbanization, economic growth, energy consumption, and trade openness on $CO_2$ emissions in Nigeria. Environ. Sci. Pollut. Res. 2016;23:12435-12443.   DOI
17 Tang CF, Tan BW. The impact of energy consumption, income and foreign direct investment on carbon dioxide emissions in Vietnam. Energy 2015;79:447-454.   DOI
18 Lin BQ, Moubarak M, Ouyang XL. Carbon dioxide emissions and growth of the manufacturing sector: Evidence for China. Energy 2014;76:830-837.   DOI
19 Wang CJ, Wang F, Zhang HG, et al. Carbon emissions decomposition and environmental mitigation policy recommendations for sustainable development in Shandong Province. Sustainability 2014;6:8164-8179.   DOI
20 Bian YW, He P, Xu H. Estimation of potential energy saving and carbon dioxide emission reduction in China based on an extended non-radial DEA approach. Energ. Policy 2013;63:962-971.   DOI
21 Perez-Suarez R, Lopez-Menendez AJ. Growing green? Forecasting $CO_2$ emissions with environmental Kuznets curves and logistic growth models. Environ. Sci. Policy 2015;54: 428-437.   DOI
22 Kang YQ, Zhao T, Wu P. Impacts of energy-related $CO_2$ emissions in China: A spatial panel data technique. Nat. Hazards 2016;81:405-421.   DOI
23 Sheng PF, Guo XH. The long-run and short-run impacts of urbanization on carbon dioxide emissions. Econ. Model. 2016;53:208-215.   DOI
24 Wu LF, Liu SF, Liu DL et al. Modelling and forecasting $CO_2$ emissions in the BRICS (Brazil, Russia, India, China, and South Africa) countries using a novel multi-variable grey model. Energy 2015;79:489-495.   DOI
25 Xu B, Lin BQ. Assessing $CO_2$ emissions in China's iron and steel industry: A dynamic vector autoregression model. Appl. Energ. 2016;161:375-386.   DOI
26 Baareh AK. Solving the carbon dioxide emission estimation problem: An artificial neural network model. J. Softw. Eng. Appl. 2013;6:338-342.   DOI
27 Behrang MA, Assareh E, Assari MR et al. Using bees algorithm and artificial neural network to forecast world carbon dioxide emission. Energ. Source 2011;33:1747-1759.   DOI
28 Huang GB, Zhu QY, Siew CK. Extreme learning machine: Theory and applications. Neurocomputing 2006;70:489-501.   DOI
29 Liu H, Tian HQ, Li YF. Four wind speed multi-step forecasting models using extreme learning machines and signal decomposing algorithms. Energ. Convers. Manage. 2015;100:16-22.   DOI
30 Omer FE. Forecasting electricity load by a novel recurrent extreme learning machines approach. Int. J. Elec. Power. 2016;78:429-435.   DOI
31 Lombardi AM. Some reasoning on the RELM-CSEP likelihood- based tests. Earth Planets Space 2014;66:286-301.
32 Yu L, Dai W, Tang L. A novel decomposition ensemble model with extended extreme learning machine for crude oil price forecasting. Eng. Appl. Artif. Intel. 2015;47:110-121.
33 Pearson K. On lines and planes of closest fit to systems of points in space. Philos. Mag. 1901;2:559-572.   DOI
34 Hotelling H. Analysis of a complex of statistical variables into principal components. J. Educ. Psychol. 1933;24:417-441.   DOI
35 Li S, Goel L, Wang P. An ensemble approach for short-term load forecasting by extreme learning machine. Appl. Energ. 2016;170:22-29.   DOI
36 Deo RC, Sahin M. Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia. Atmos. Res. 2015;153:512-525.   DOI
37 Zhang K, Luo MX. Outlier-robust extreme learning machine for regression problems. Neurocomputing 2015;151:1519-1527.   DOI
38 Energy Research Institute National Development And Reform Commission. The comprehensive report of China sustainable development of energy and carbon emission scenarios analysis [cited May, 2003]. Available from: http://www.docin.com/p-419481261.html.
39 Asongu S, Montasser GE, Toumi H. Testing the relationships between energy consumption, $CO_2$ emissions, and economic growth in 24 African countries: A panel ARDL approach. Environ. Sci. Pollut. Res. 2015;23:6563-6573.
40 Auffhammer M, Carson RT. Forecasting the path of China's $CO_2$ emissions using province-level information. J. Environ. Econ. Manag. 2008;55:229-247.   DOI
41 Farhani S, Ozturk I. Causal relationship between $CO_2$ emissions, real GDP, energy consumption, financial development, trade openness, and urbanization in Tunisia. Environ. Sci. Pollut. Res. 2015;22:15663-15676.   DOI
42 Song JK. China's carbon emissions prediction model based on support vector regression. J. China Univ. Pet. 2012;36: 182-187.
43 Aydin G, Jang H, Topal E. Energy consumption modeling using artificial neural networks: The case of the world's highest consumers. Energ. Source. Part B. 2016;11:212-219.   DOI
44 Jiang X, Zhu K, Wang S. The potential for reducing China's carbon dioxide emissions: Role of foreign-invested enterprises. Global Environ. Chang. 2015;35:22-30.   DOI
45 Gurney KR. Global change: China at the carbon crossroads. Nature 2009;458:977-979.   DOI
46 Holditch SA, Chianelli RR. Factors that will influence oil and gas supply and demand in the 21st century. MRS Bull. 2008;33:317-323.   DOI
47 Longwell HJ. The future of the oil and gas industry: Past approaches, new challenges. World Energ. 1998;5:100-104.
48 Say NP, Yucel M. Energy consumption and $CO_2$ emissions in Turkey: Empirical analysis and future projection based on an economic growth. Energ. Policy 2006;34:3870-3876.   DOI