Determining China's CO2 emissions peak with a dynamic nonlinear artificial neural network approach and scenario analysis

The global community and the academic world have paid great attention to whether and when China's carbon dioxide (CO2) emissions will peak. Our study investigates the issue with the Nonlinear Auto Regressive model with exogenous inputs (NARX), a dynamic nonlinear artificial neural network that has not been applied previously to this question. The key advance over previous models is the inclusion of feedback mechanisms such as the influence of past CO2 emissions on current emissions. The results forecast that the peak of China's CO2 emissions will occur in 2029, 2031 or 2035 at the level of 10.08, 10.78 and 11.63 billion tonnes under low-growth, benchmark moderate-growth, and high-growth scenarios. Based on the methodology of the mean impact value (MIV), we differentiate and rank the importance of the influence factors on CO2 emissions whereas previous studies included but did not rank factors. We suggest that China should choose the moderate growth development road and achieve its peak target in 2031, focusing on reducing CO2 emissions as a percent of GDP, less carbon-intensive industrialization, and choosing technologies that reduce CO2 emissions from coal or increasing the use of less carbon-intensive fuels.

[1]  Farid Atry,et al.  Multi-step ahead forecasts for electricity prices using NARX: A new approach, a critical analysis of one-step ahead forecasts , 2009 .

[2]  Shen Le,et al.  2050 Energy Consumption Projection for China , 2015 .

[3]  Charlie Wilson,et al.  Diagnostic indicators for integrated assessment models of climate policy , 2015 .

[4]  Valerie J. Karplus,et al.  Carbon emissions in China: How far can new efforts bend the curve? , 2016 .

[5]  Yi Zeng,et al.  Multifactor-influenced energy consumption forecasting using enhanced back-propagation neural network , 2017 .

[6]  Fang Jingyun.  2050 Carbon Emissions Projection for China(Carbon Emissions and Social Development,IV) , 2010 .

[7]  Katsuya Ito.  CO2 emissions, renewable and non-renewable energy consumption, and economic growth: Evidence from panel data for developing countries , 2016 .

[8]  N. Stern,et al.  China's changing economy: implications for its carbon dioxide emissions , 2016 .

[9]  Lucila Maria de Souza Campos,et al.  CO2 emissions: A quantitative analysis among the BRICS nations , 2018 .

[10]  J. Tollefson.  China’s carbon emissions could peak sooner than forecast , 2016, Nature.

[11]  Luis Gomez-Echeverri,et al.  China Human Development Report 2009/10: China and a Sustainable Future - Towards a Low Carbon Economy and Society , 2010 .

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

[13]  Nan Zhou,et al.  China's Energy and Carbon Emissions Outlook to 2050 , 2011 .

[14]  Dunnan Liu,et al.  Can China achieve its carbon emission peaking? A scenario analysis based on STIRPAT and system dynamics model , 2018, Ecological Indicators.

[15]  Leo Schrattenholzer,et al.  MESSAGE-MACRO: Linking an energy supply model with a macroeconomic module and solving it iteratively , 2000 .

[16]  C. Weber,et al.  The drivers of Chinese CO2 emissions from 1980 to 2030 , 2008 .

[17]  Ajay Gambhir,et al.  A hybrid modelling approach to develop scenarios for China's carbon dioxide emissions to 2050 , 2013 .

[18]  H. Troy Nagle,et al.  Performance of the Levenberg–Marquardt neural network training method in electronic nose applications , 2005 .

[19]  Sadig Mammadli,et al.  Financial time series prediction using artificial neural network based on Levenberg-Marquardt algorithm , 2017 .

[20]  Marcello Farina,et al.  Environmental Over-Threshold Event Forecasting using NARX Models , 2011 .

[21]  Qimin Chai,et al.  Modeling an emissions peak in China around 2030: Synergies or trade-offs between economy, energy and climate security , 2014 .

[22]  D. L. Kelly,et al.  Integrated Assessment Models For Climate Change Control∗ , 1998 .

[23]  Jim Watson,et al.  Scenario analysis of China’s emissions pathways in the 21st century for low carbon transition , 2010 .

[24]  Nicklas Forsell,et al.  Greenhouse gas emissions from current and enhanced policies of China until 2030: Can emissions peak before 2030? , 2016 .

[25]  Carman K.M. Lee,et al.  A Comparison between Neural Networks and Traditional Forecasting Methods: A Case Study , 2009 .

[26]  Xu Guangyue,et al.  An Empirical Study on the Environmental Kuznets Curve for China’s Carbon Emissions: Based on Provincial Panel Data , 2011 .

[27]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.

[28]  J. Weyant.  Some Contributions of Integrated Assessment Models of Global Climate Change , 2017, Review of Environmental Economics and Policy.

[29]  Alireza Talaei,et al.  Predicting oil price movements: A dynamic Artificial Neural Network approach , 2014 .

[30]  Yi-Ming Wei,et al.  Socioeconomic impact assessment of China's CO2 emissions peak prior to 2030 , 2017 .

[31]  Guo Chao-xian,et al.  Forecast of China's carbon emissions based on STIRPAT model , 2010 .

[32]  Nicholas Stern,et al.  China's post-coal growth , 2016 .

[33]  Zheng Wang,et al.  Energy structure change and carbon emission trends in China , 2016 .

[34]  Zheng Hu,et al.  Peak energy consumption and CO2 emissions in China , 2014 .

[35]  Vijander Singh,et al.  ANN-based estimator for distillation using Levenberg-Marquardt approach , 2007, Eng. Appl. Artif. Intell..

[36]  Wang Zheng,et al.  Simulation on China's Economy and Prediction on Energy Consumption and Carbon Emission under Optimal Growth Path , 2009 .

[37]  Yi-Ming Wei,et al.  How to peak carbon emissions in China's power sector: A regional perspective , 2018, Energy Policy.

[38]  Marcello Farina,et al.  Forecasting peak air pollution levels using NARX models , 2009, Eng. Appl. Artif. Intell..

[39]  Jinhang Chen,et al.  An Empirical Study on China’s Energy Supply-and-Demand Model Considering Carbon Emission Peak Constraints in 2030 , 2017 .