Comparison of CO2 Emissions Prediction in Vehicles Using Different Artificial Neural Network Models

Year 2024, , 309 - 324, 11.07.2024

Emrah Aslan

https://doi.org/10.21605/cukurovaumfd.1513998

Abstract

Climate change is one of the greatest environmental threats to humanity. Carbon dioxide (CO2) is one of the main causes of the greenhouse effect in climate change. The transportation sector is one of the major sources of CO2 emissions. This paper presents an artificial neural network (ANN) model for estimating the instantaneous CO2 emissions of vehicles. A comprehensive approach using three regression models, namely Linear Regression, XGBoost Regressor and K-Nearest Neighbors Regressor, is used to predict CO2 emissions from vehicles. The research focuses on leveraging the capabilities of these artificial neural networks to predict and analyze CO2 emissions from vehicles. The use of different models allows for a comparative evaluation of their performance in terms of accuracy and efficiency. This method, which provides high accuracy and applicability, uses parameters such as engine displacement, cylinder, urban and non-urban fuel consumption as predictors of exhaust emissions. The importance of each parameter to emission predictions is comprehensively analyzed by comparing results such as test and training accuracy, root mean square error, mean absolute error, R2 score. This study aims to contribute to the advancement of CO2 emission estimation methodologies, especially in the context of vehicle emissions. The findings of this research are important for policy makers, environmentalists and automotive engineers seeking sustainable solutions to reduce carbon footprints in the transportation sector.

Keywords

CO2 emissions, ANN, Fuel Consumption

Araçlarda CO2 Emisyonlarının Farklı Yapay Sinir Ağı Modelleri Kullanılarak Tahminlerinin Karşılaştırılması

Abstract

İklim değişikliği, insanlık için en büyük çevresel tehlikelerden biridir. İklim değişikliğinde karbondioksit (CO2), sera etkisinin başlıca sebeplerindendir. Ulaşım sektörü, büyük CO2 emisyon kaynaklarından birini oluşturmaktadır. Bu makale, araçlarının anlık CO2 emisyonlarını tahmin etmek için bir yapay sinir ağı (YSA) modeli sunmaktadır. Araçlarda CO2 emisyonlarını tahmin etmek için Linear Regresyon, XGBoost Regresör ve K-Nearest Neighbours Regresörü olmak üzere üç regresyon modeli kullanılarak kapsamlı bir yaklaşım kullanılmıştır. Araştırma, araçlardaki CO2 emisyonlarını tahmin etmek ve analiz etmek için bu yapay sinir ağlarının yeteneklerinden yararlanmaya odaklanmaktadır. Farklı modellerin kullanılması, doğruluk ve verimlilik açısından performanslarının karşılaştırmalı olarak değerlendirilmesine olanak sağlamaktadır. Yüksek doğruluk ve uygulanabilirlik sağlayan bu yöntem, motor hacmi, silindiri, şehir içi ve şehir dışı yakıt tüketimi gibi parametreler ile egzoz emisyonlarının öngörücüleri olarak kullanmaktadır. Her parametrenin emisyon tahminlerine olan önemi, test ve eğitim doğruluğu, kök ortalama kare hatası, ortalama mutlak hata, R2 skor gibi sonuçlar karşılaştırılarak kapsamlı bir şekilde analiz edilmiştir. Bu çalışma, özellikle araç emisyonları bağlamında CO2 emisyon tahmin metodolojilerinin ilerlemesine katkıda bulunmayı amaçlamaktadır. Bu araştırmanın bulguları, ulaştırma sektöründe karbon ayak izlerini azaltmak için sürdürülebilir çözümler arayan politika yapıcılar, çevreciler ve otomotiv mühendisleri için önem taşımaktadır.

Keywords

CO2 emisyonu, Yapay sinir ağı, Yakıt tüketimi

References

• 1. Özüpak, Y., 2024. Evrişimli Sinir Ağı (ESA) Mimarileri ile Hücre Görüntülerinden Sıtmanın Tespit Edilmesi. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 39(1), 197-210.
• 2. Zacharof, N., Fontaras, G., Ciuffo, B., Tansini, A., Prado-Rujas, I., 2021. An Estimation of Heavy-duty Vehicle Fleet CO2 Emissions Based on Sampled Data. Transport. Res. Transport Environ., 94, 102784.
• 3. Ganesan, P., Rajakarunakaran, S, Thirugnanasambandam, M, Devaraj, D., 2015. Artificial Neural Network Model to Predict the Diesel Electric Generator Performance and Exhaust Emissions. Energy, 83, 115-124.
• 4. Çay, Y., 2013. Prediction of a Gasoline Engine Performance with Artificial Neural Network. Fuel, 111, 324-331.
• 5. Hawkes, A.D., 2010. Estimating Marginal CO2 Emissions Rates for National Electricity Systems. Energy Policy, 38, 5977-5987.
• 6. Labecki, L., Cairns, A., Xia, J., Megaritis, A., Zhao, H., Ganippa, L.C., 2012. Combustion and Emission of Rapeseed Oil Blends in Diesel Engine. Applied Energy, 95, 139-146.
• 7. Tasdemir, S., Saritas, I., Ciniviz, M., Allahverdi, N., 2011. Artificial Neural Network and Fuzzy Expert System Comparison for Prediction of Performance and Emission Parameters on a Gasoline Engine. Expert Systems with Applications, 38, 13912-23.
• 8. Anderson, T.R., Hawkins, E., Jones, P.D., 2016. CO2, the Greenhouse Effect and Global Warming: From the Pioneering Work of Arrhenius and Callendar to Today’s Earth System Models. Endeavour, 40(3), 178-187.
• 9. Zeng, W., Miwa, T., Morikawa, T., 2016. Prediction of Vehicle CO2 Emission and Its Application to Eco-routing Navigation. Transportation Research Part C: Emerging Technologies, 68, 194-214.
• 10. Oduro, S., Metia, S., Duc, H., Ha, Q., 2013. CO2 Vehicular Emission Statistical Analysis with Instantaneous Speed and Acceleration as Predictor Variables. In Proceedings of the International Conference on Control, Automation and Information Sciences, 158-163.
• 11. Razak, N.H., Hashim, H., Yunus, N.A., Klemes, J.J., 2022. Integrated Linear Programming and Analytical Hierarchy Process Method for Diesel/Biodiesel/Butanol in Reducing Diesel Emissions. Journal of Cleaner Production, 337, 130297.
• 12. Shim, E., Park, H., Bae, C., 2018. Intake Air Strategy for Low HC and CO Emissions in Dual-fuel (CNG-Diesel) Premixed Charge Compression Ignition Engine. Applied Energy, 225, 1068-77.
• 13. Prabhu, A.V., Avinash, A., Brindhadevi, K., Pugazhendhi, A., 2021. Performance and Emission Evaluation of Dual Fuel CI Engine Using Preheated Biogas-air Mixture. Science of the Total Environment, 754, 142389.
• 14. Soukht, S.H., Taghavifar, H., Jafarmadar, S., 2017. Experimental and Numerical Consideration of the Effect of CeO2 Nanoparticles on Diesel Engine Performance and Exhaust Emission with the Aid of Artificial Neural Network. Applied Thermal Engineering, 113, 663-72.
• 15. Alfaseeh, L., Tu, R., Farooq, B., Hatzopoulou, M., 2020. Greenhouse Gas Emission Prediction on Road Network Using Deep Sequence Learning. Transport. Res. Transport Environ, 88, 102593.
• 16. Claudio, M., Daniela, M., Alessandro, D.M., Ezio S., 2021. A Deep Neural Network Based Model for the Prediction of Hybrid Electric Vehicles Carbon Dioxide Emissions. Energy and AI, 5, 100073, 2666-5468.
• 17. Jigu, S., Sungwook, P., 2023. Optimizing Model Parameters of Artificial Neural Networks to Predict Vehicle Emissions. Atmospheric Environment, 294, 119508, 1352-2310.
• 18. Natarajan, Y., Wadhwa, G., Sri, K.R., Paul, A., 2023. Forecasting Carbon Dioxide Emissions of Light-Duty Vehicles with Different Machine Learning Algorithms. Electronics, 12, 2288.
• 19. Al-Nefaie, A.H., Aldhyani, T.H.H., 2023. Predicting CO2 Emissions from Traffic Vehicles for Sustainable and Smart Environment Using a Deep Learning Model. Sustainability, 15, 7615.
• 20. Dong, T., Zhen, Z., Lun, H., Jinchong, P., Yang, X., 2023. Prediction of Cold Start Emissions for Hybrid Electric Vehicles Based on Genetic Algorithms and Neural Networks. Journal of Cleaner Production, 420, 138403.
• 21. Paul, D., Dieudonné, T., Guillaume, C., 2023. Method and Evaluations of the Effective Gain of Artificial Intelligence Models for Reducing CO2 Emissions. Journal of Environmental Management, 331, 117261, 0301-4797.
• 22. Wang, Z., Feng, K., 2024. NOx Emission Prediction for Heavy-Duty Diesel Vehicles Based on Improved GWO-BP Neural Network. Energies, 17, 336.
• 23. Mądziel, M., 2024. Instantaneous CO2 Emission Modelling for a Euro 6 Start-Stop Vehicle Based on Portable Emission Measurement System Data and Artificial Intelligence Methods. Environ Sci Pollut Res, 31, 6944-6959.
• 24. CO2 Emission by Vehicles Dataset, https://open.canada.ca/data/en/dataset/98f1a129-f628-4ce4-b24d-6f16bf24dd64#wb-auto-6, Erişim tarihi: 02.02.2024.