A Forecast of CO2 Emissions Based on the Fuel Consumption Rating of a Particular Vehicle
DOI:
https://doi.org/10.54097/ew5myj79Keywords:
Carbon emissions, multiple linear regression analysis, automobile road testing.Abstract
The accumulation of carbon dioxide will not only cause global warming but also cause a series of catastrophic consequences and cause irreversible damage to the earth's ecology. The prediction of carbon dioxide emissions from light-duty vehicles can provide decision-making support for consumers when purchasing cars and is beneficial to consumers in purchasing environmentally friendly cars. This paper constructs a vehicle carbon dioxide emission model based on a multiple linear regression model, using the four indicators of vehicle engine size, vehicle fuel consumption, Hwy (L/100km), and Comb (L/100km) as output variables. The quantity is the predictor variable. The correlation coefficient of this study is 0.9675. The regression equation of this linear regression model is Y=22.2344+2.7157X1+32.9843X2+26.6259X3-39.1429X4. The order of impact of the four indicators studied on carbon emissions is Comb (L/100km), vehicle fuel consumption, Hwy (L/100km), and vehicle engine size. The determination of carbon emissions of specific models of new light vehicles can refer to the multiple linear regression model proposed in this study.
Downloads
References
Li Shuang, Cao Wenjing, Lu Bin. Research on optimization of my country's energy consumption structure under the constraints of low carbon goals. Journal of Shanxi University (Philosophy and Social Sciences Edition), 2015, 38 (04): 108 - 115.
Chen Liang, Wang Jinhong, He Tao, et al. Research on regional transportation carbon emission prediction based on SVR. Transportation System Engineering and Information, 2018, 18 (02): 13 - 19.
Liu Guangwei, Zhao Tao. China’s carbon emission intensity forecast and tertiary industry proportion test analysis. Economic Management, 2012, 34 (05): 141 - 152.
Qu Shenning, Guo Chaoxian. Research on China’s carbon emission peak prediction based on STIRPAT model. Chinese Population·Resources and Environment, 2010, 20 (12): 10 - 15.
Zhao Xi, Qi Jianmin, Liu Guangwei. China’s carbon emission prediction based on discrete second-order difference algorithm. Arid Area Resources and Environment, 2013, 27 (01): 63 - 69.
Zhu Yongbin, Wang Zheng, Pang Li, et al. Peak prediction of energy consumption and carbon emissions in China based on economic simulation. Acta Geographica Sinica, 2009, 64 (08): 935-944.
Xiao Zhihong, Wang Minghao. Combination model and prediction of China’s carbon emissions. Journal of Chongqing Technology and Business University (Natural Science Edition), 2016, 33 (01): 9 - 15.
Zhang Fafa, Wang Yanxu. Research on world carbon emission prediction model integrating system clustering and BP neural network. Practice and Understanding of Mathematics, 2016, 46 (01): 77 - 84.
Ji Guangyue. Application of BP neural network model based on gray correlation analysis in China's carbon emission prediction. Practice and Understanding of Mathematics, 2014, 44 (14): 243 - 249.
Zhao Jinyuan, Ma Zhen, Tang Hailiang. Comparison of BP neural network and multiple linear regression models in carbon emission prediction. Science and Technology and Industry, 2020, 20 (11): 172 - 176.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.







