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

Nowadays, with the burgeoning development of economy, CO2 emissions increase rapidly in China. It has become a common concern to seek effective methods to forecast CO2 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 CO2 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 CO2 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 CO2 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 CO2 emission prediction.

[1]  T. Zhao,et al.  Impacts of energy-related CO2 emissions in China: a spatial panel data technique , 2016, Natural Hazards.

[2]  Sifeng Liu,et al.  Modelling and forecasting CO2 emissions in the BRICS (Brazil, Russia, India, China, and South Africa) countries using a novel multi-variable grey model , 2015 .

[3]  K. Gurney.  Global change: China at the carbon crossroads , 2009, Nature.

[4]  Shandong Province,et al.  Carbon Emissions Decomposition and Environmental Mitigation Policy Recommendations for Sustainable Development in , 2014 .

[5]  Mohamed Moubarak,et al.  Carbon dioxide emissions and growth of the manufacturing sector: Evidence for China , 2014 .

[6]  Ilhan Ozturk,et al.  Causal relationship between CO2 emissions, real GDP, energy consumption, financial development, trade openness, and urbanization in Tunisia , 2015, Environmental Science and Pollution Research.

[7]  Bin Xu,et al.  Assessing CO2 emissions in China’s iron and steel industry: A dynamic vector autoregression model , 2016 .

[8]  Antonio Rodríguez Andrés,et al.  Determinants of CO2 emissions in Brazil and Russia between 1992 and 2011: A decomposition analysis , 2016 .

[9]  Minxia Luo,et al.  Outlier-robust extreme learning machine for regression problems , 2015, Neurocomputing.

[10]  Wei Li,et al.  Decomposing Industrial Energy-Related CO 2 Emissions in Yunnan Province, China: Switching to Low-Carbon Economic Growth , 2016 .

[11]  Gokhan Aydin,et al.  The Modeling of Coal-related CO2 Emissions and Projections into Future Planning , 2014 .

[12]  Hui Liu,et al.  Four wind speed multi-step forecasting models using extreme learning machines and signal decomposing algorithms , 2015 .

[13]  S. Law,et al.  Dynamic impact of urbanization, economic growth, energy consumption, and trade openness on CO2 emissions in Nigeria , 2016, Environmental Science and Pollution Research.

[14]  Rigoberto Pérez-Suárez,et al.  Growing green? Forecasting CO2 emissions with Environmental Kuznets Curves and Logistic Growth Models , 2015 .

[15]  Khalid Ahmed.  The sheer scale of China’s urban renewal and CO2 emissions: multiple structural breaks, long-run relationship, and short-run dynamics , 2016, Environmental Science and Pollution Research.

[16]  Ali Azadeh,et al.  INTEGRATION OF GENETIC ALGORITHM, COMPUTER SIMULATION AND DESIGN OF EXPERIMENTS FOR FORECASTING ELECTRICAL ENERGY CONSUMPTION , 2007 .

[17]  Erkan Topal,et al.  Energy consumption modeling using artificial neural networks: The case of the world’s highest consumers , 2016 .

[18]  Stephen A. Holditch,et al.  Factors That Will Influence Oil and Gas Supply and Demand in the 21st Century , 2008 .

[19]  Gokhan Aydin,et al.  The Development and Validation of Regression Models to Predict Energy-related CO2 Emissions in Turkey , 2015 .

[20]  Nuriye Say,et al.  Energy consumption and CO2 emissions in Turkey: Empirical analysis and future projection based on an economic growth , 2006 .

[21]  A. Lombardi,et al.  Some reasoning on the RELM-CSEP likelihood-based tests , 2014, Earth, Planets and Space.

[22]  Xuemei Jiang,et al.  The potential for reducing China's carbon dioxide emissions: Role of foreign-invested enterprises , 2015 .

[23]  Vivek Utgikar,et al.  Energy forecasting: Predictions, reality and analysis of causes of error , 2006 .

[24]  Yung‐ho Chiu,et al.  Driving factors behind carbon dioxide emissions in China: A modified production-theoretical decomposition analysis , 2015 .

[25]  Ling Tang,et al.  A novel decomposition ensemble model with extended extreme learning machine for crude oil price forecasting , 2016, Eng. Appl. Artif. Intell..

[26]  Liying Li,et al.  Carbon dioxide emission drivers for a typical metropolis using input–output structural decomposition analysis , 2013 .

[27]  Song Jie-kun,et al.  China’s carbon emissions prediction model based on support vector regression , 2012 .

[28]  Mohamed Moubarak,et al.  Decomposition analysis: Change of carbon dioxide emissions in the Chinese textile industry , 2013 .

[29]  Song Li,et al.  An ensemble approach for short-term load forecasting by extreme learning machine , 2016 .

[30]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[31]  P. F. González,et al.  The driving forces behind changes in CO2 emission levels in EU-27. Differences between member states , 2014 .

[32]  Pengfei Sheng,et al.  The Long-run and Short-run Impacts of Urbanization on Carbon Dioxide Emissions , 2016 .

[33]  Wei Li,et al.  Decomposition of China’s CO2 emissions from agriculture utilizing an improved Kaya identity , 2014, Environmental Science and Pollution Research.

[34]  Abdel Karim Baareh.  Solving the Carbon Dioxide Emission Estimation Problem: An Artificial Neural Network Model , 2013 .

[35]  Haiyan Xu,et al.  Modelling and forecasting CO 2 emissions in the BRICS ( Brazil , Russia , India , China , and South Africa ) countries using a novel multivariable grey model , 2014 .

[36]  Qi Li,et al.  Coupling analysis of China’s urbanization and carbon emissions: example from Hubei Province , 2016, Natural Hazards.

[37]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[38]  Weidong Liu,et al.  Temporal and spatial variations in consumption-based carbon dioxide emissions in China , 2014 .

[39]  M. A. Behrang,et al.  Using Bees Algorithm and Artificial Neural Network to Forecast World Carbon Dioxide Emission , 2011 .

[40]  R. Deo,et al.  Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia , 2015 .

[41]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[42]  Hassen Toumi,et al.  Testing the relationships between energy consumption, CO2 emissions, and economic growth in 24 African countries: a panel ARDL approach , 2015, Environmental Science and Pollution Research.

[43]  C. Tang,et al.  The impact of energy consumption, income and foreign direct investment on carbon dioxide emissions in Vietnam , 2015 .

[44]  M. Auffhammer,et al.  Forecasting the Path of China's CO2 Emissions Using Province Level Information , 2007 .

[45]  Lixiao Zhang,et al.  Scenario analysis of urban energy saving and carbon abatement policies: A case study of Beijing city, China , 2012 .

[46]  P. He,et al.  Estimation of potential energy saving and carbon dioxide emission reduction in China based on an extended non-radial DEA approach , 2013 .

[47]  Ömer Faruk Ertuğrul,et al.  Forecasting electricity load by a novel recurrent extreme learning machines approach , 2016 .