Issue |
Sci. Tech. Energ. Transition
Volume 79, 2024
|
|
---|---|---|
Article Number | 15 | |
Number of page(s) | 21 | |
DOI | https://doi.org/10.2516/stet/2024014 | |
Published online | 15 March 2024 |
Regular Article
Application of various machine learning algorithms in view of predicting the CO2 emissions in the transportation sector
1
Department of Computer Engineering, Faculty of Engineering-Architecture, Yozgat Bozok University, Yozgat, Türkiye
2
Department of Mechanical Engineering, Faculty of Engineering-Architecture, Yozgat Bozok University, Yozgat, Türkiye
3
Department of Mechanical Engineering, Faculty of Engineering, Duzce University, Düzce, Türkiye
4
Department of Automotive Technology, Yozgat Vocational School, Yozgat Bozok University, Yozgat, Türkiye
5
Department of Computer Technology, Yozgat Vocational School, Yozgat Bozok University, Yozgat, Türkiye
* Corresponding author: zeki.yilbasi@bozok.edu.tr
Received:
11
January
2024
Accepted:
8
February
2024
This study applies three different artificial intelligence algorithms (Multi-layer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM)) to estimate CO2 emissions in Türkiye’s transportation sector. The input parameters considered are Energy consumption (ENERGY), Vehicle Kilometers (VK), POPulation (POP), Year (Y), and Gross Domestic Product Per Capita (GDP). Strong correlations are observed, with ENERGY having the highest correlation followed by VK, POP, Y, and GDP. Four scenarios are designed based on the correlation effect: scenario 1 (ENERGY/VK/POP/Y/GDP), scenario 2 (ENERGY/VK/POP/Y), scenario 3 (ENERGY/VK/POP), and scenario 4 (ENERGY/VK). Experiments compare their effects on CO2 emissions using statistical indicators (R2, RMSE, MSE, and MAE). Across all scenarios and algorithms, R2 values range from 0.8969 to 0.9886, and RMSE values range from 0.0333 to 0.1007. The XGBoost algorithm performs best in scenario 4. Artificial intelligence algorithms prove successful in estimating CO2 emissions. This study has significant implications for policymakers and stakeholders. It highlights the need to review energy investments in transportation and implement regulations, restrictions, legislation, and obligations to reduce emissions. Artificial intelligence algorithms offer the potential for developing effective strategies. Policymakers can use these insights to prioritize sustainable energy investments. In conclusion, this study provides insights into the relationship between input parameters and CO2 emissions in the transportation sector. It emphasizes the importance of proactive measures and policies to address the sector’s environmental impact. It also contributes to the understanding of AI-assisted CO2 emissions forecasting in the transport sector, potentially informing future policy decisions aimed at emission reduction and sustainable transport development.
Key words: CO2 emissions / Transportation sector / Artificial intelligence / Machine learning algorithm / Statistical indicators
© The Author(s), published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.