Application of various machine learning algorithms in view of predicting the CO 2 emissions in the transportation sector
Science and Technology for Energy Transition · 2024 · 79 · 15
DOI: 10.2516/stet/2024014 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science and Technology for Energy Transition, online erschienen am 15.03.2024. Verfasst von Gökalp Çınarer und 4 weiteren Autor:innen. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 95 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study applies three different artificial intelligence algorithms (Multi-layer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM)) to estimate CO 2 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 CO 2 emissions using statistical indicators ( R 2 , RMSE, MSE, and MAE). Across all scenarios and algorithms, R 2 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 CO 2 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 CO 2 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 CO 2 emissions forecasting in the transport sector, potentially informing future policy decisions aimed at emission reduction and sustainable transport development.
Zitieren
APA
Çınarer, G., Yeşilyurt, M. K., Ağbulut, Ü., Yılbaşı, Z., & Kılıç, K. (2024). Application of various machine learning algorithms in view of predicting the CO 2 emissions in the transportation sector. Science and Technology for Energy Transition, 79, 15. https://doi.org/10.2516/stet/2024014
Vancouver
Çınarer G, Yeşilyurt MK, Ağbulut Ü, Yılbaşı Z, Kılıç K. Application of various machine learning algorithms in view of predicting the CO 2 emissions in the transportation sector. Science and Technology for Energy Transition. 2024;79:15. doi:10.2516/stet/2024014
BibTeX
@article{narer2024,
author = {Çınarer, Gökalp and Yeşilyurt, Murat Kadir and Ağbulut, Ümit and Yılbaşı, Zeki and Kılıç, Kazım},
title = {Application of various machine learning algorithms in view of predicting the CO 2 emissions in the transportation sector},
journal = {Science and Technology for Energy Transition},
year = {2024},
volume = {79},
pages = {15},
doi = {10.2516/stet/2024014}
}
EUVIMED