Makine Öğrenmesi Algoritmaları Kullanarak Şehirlere Göre Elektrikli Araç Menzillerinin Tahmin Edilmesi

Abstract

Bu çalışma, yalnızca araç içi verilere odaklanan geleneksel modellerin temel kısıtlamalarını ele alarak; gelişmiş makine öğrenimi (ML) algoritmalarının yanı sıra şehir ölçeğindeki coğrafi ve altyapısal değişkenleri de dahil eden, veri odaklı ve yenilikçi bir çerçeve sunmaktadır. Amerika Birleşik Devletleri genelinde 65.000'den fazla gerçek araçtan elde edilen kapsamlı bir veri setini kullanan araştırma; iklimsel faktörler, trafik akışı ve bölgesel altyapı gibi kentsel bağlam unsurlarının, elektrikli araç (EV) enerji tüketiminde belirleyici bir rol oynadığını ortaya koymaktadır. Random Forest (RF), Gradient Boosting (GB) ve Sinir Ağları (NN) yöntemlerinin karşılaştırıldığı titiz bir performans değerlendirmesi sonucunda RF'nin en etkili yaklaşım olduğu tespit edilmiştir; bu yöntem, 0,994'lük R² değeri ve 7,387 millik RMSE değeri ile olağanüstü bir tahmin doğruluğu sağlayarak literatürdeki mevcut modelleri önemli ölçüde geride bırakmıştır. Nihayetinde bu sonuçlar, şehir ölçeğindeki verilerin sistematik bir şekilde entegre edilmesinin menzil tahminlerinin hassasiyetini büyük ölçüde artırdığını göstermektedir; böylece söz konusu yaklaşım; menzil kaygısını hafifletmek, tüketici beklentilerine yön vermek ve şehir plancıları ile politika yapıcıları şarj ağlarının optimize edilmesi ve sürdürülebilir elektrikli mobilitenin geliştirilmesi konularında güvenilir, veri destekli bir temel ile donatmak adına pratik bir çözüm sunmaktadır.

Keywords

• şarj edilebilir hibrit
• elektirikli araç
• makine öğrenmesi
• mesafe tahmini
• şehir

Predicting Electric Vehicle Ranges Based on Cities Using Machine Learning Algorithms

Abstract

This study introduces a novel, data-driven framework for predicting electric vehicle (EV) range by incorporating city-level geographic and infrastructural variables alongside advanced machine learning (ML) algorithms, thereby addressing the key limitations of traditional models that focus solely on internal vehicle metrics. Using a comprehensive dataset of more than 65,000 real-world vehicles across the United States, the research highlights that urban context—including climatic factors, traffic flow, and regional infrastructure—is a crucial determinant of EV energy consumption. A rigorous performance evaluation comparing Random Forest (RF), Gradient Boosting (GB), and Neural Networks (NN) identifies RF as the most effective approach, delivering exceptional predictive accuracy with an R2 of 0.994 and an RMSE of 7.387 miles, significantly outperforming existing models in the literature. Ultimately, these results demonstrate that systematically integrating urban-level data substantially enhances the precision of range predictions, offering a practical solution to alleviate range anxiety, guide consumer expectations, and equip urban planners and policymakers with a reliable, data-backed foundation for optimizing charging networks and advancing sustainable electric mobility.

Keywords

• Electric vehicle
• plug-in hybrid
• machine learning
• range prediction
• cities

References

1. Abou Elassad, Z. E., Mousannif, H., Al Moatassime, H., & Karkouch, A. (2020). The application of machine learning techniques for driving behavior analysis: A conceptual framework and a systematic literature review. Engineering Applications of Artificial Intelligence, 87, Article 103312. https://doi.org/10.1016/j.engappai.2019.103312
2. Al-Refai, G., Elmoaqet, H., & Ryalat, M. (2022). In-vehicle data for predicting road conditions and driving style using machine learning. Applied Sciences, 12(18), Article 8928. https://doi.org/10.3390/app12188928
3. Altuntaş, T., & Atalan, A. (2024). Process capability analysis of prediction data of ML algorithms. Ekonomi İşletme ve Maliye Araştırmaları Dergisi, 6(2), 208–220. https://doi.org/10.38009/ekimad.1519608
4. Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE). Geoscientific Model Development Discussions, 7(1), 1525–1534. https://doi.org/10.5194/gmdd-7-1525-2014
5. Costa, V. G., & Pedreira, C. E. (2023). Recent advances in decision trees: An updated survey. Artificial Intelligence Review, 56(5), 4765–4800. https://doi.org/10.1007/s10462-022-10275-5
6. Demirbilek, M., & Özulukale Demirbilek, S. (2023). Google Yorumları Üzerinden Makine Öğrenme Yöntemleri ve Amazon Comprehend ile Duygu Analizi: İç Anadoluda Bir Üniversite Örneği. Journal of University Research, 6(4), 452–461. https://doi.org/10.32329/uad.1383794
7. Demirbilek, M., & Özulukale Demirbilek, S. (2025). Restaurant Review Sentiment and SWOT Analysis: using AWS and GPT-4 Large Language Models. Acta Infologica, 9(2), 491–511. https://doi.org/10.26650/acin.1681039
8. Dunka, V., Punukollu, P., Kodali, S., Punukollu, M., Burugu, S., & Yerneni, R. P. (2022). AI-driven predictive analytics for fleet management optimization in logistics and transportation: Leveraging machine learning for route planning, vehicle allocation, and predictive maintenance. Newark Journal of Human-Centric AI and Robotics Interaction, 2, 359–396.

9. Elmi, S., & Tan, K.-L. (2021). DeepFEC: Energy consumption prediction under real-world driving conditions for smart cities. In Proceedings of the Web Conference 2021 (pp. 1880–1890). https://doi.org/10.1145/3442381.3449983
10. Gurusamy, A., Ashok, B., & Mason, B. (2023). Prediction of electric vehicle driving range and performance characteristics: A review on analytical modeling strategies with its influential factors and improvisation techniques. IEEE Access, 11, 131521–131548. https://doi.org/10.1109/ACCESS.2023.3334620
11. Hinton, G. E. (1992). How neural networks learn from experience. Scientific American, 267(3), 144–151. https://doi.org/10.1038/scientificamerican0992-144
12. Kaggle. (n.d.). Electric vehicle population data [Data set]. https://www.kaggle.com/datasets/ratikkakkar/electric-vehicle-population-data
13. Kleyko, D., Hostettler, R., Birk, W., & Osipov, E. (2015). Comparison of machine learning techniques for vehicle classification using road side sensors. In 2015 IEEE 18th International Conference on Intelligent Transportation Systems (pp. 572–577). IEEE. https://doi.org/10.1109/ITSC.2015.100
14. Lee, R., & Brown, S. (2021). Evaluating the role of behavior and social class in electric vehicle adoption and charging demands. iScience, 24(8), Article 102830. https://doi.org/10.1016/j.isci.2021.102830
15. Lee, Y., Kim, W.-S., & Han, J. (2025). Comparative study of thermal management systems in electric vehicles: Exergy and energy efficiency under cold climate conditions. Renewable Energy, Article 123926. https://doi.org/10.1016/j.renene.2025.123926
16. Liang, X., Song, H., Wu, G., Guo, Y., & Zhang, S. (2024). Complex traffic flow model for analysis and optimization of fuel consumption and emissions at large roundabouts. Sustainability, 16(21), Article 9464. https://doi.org/10.3390/su16219464
17. Lin, L., Wang, F., Xie, X., & Zhong, S. (2017). Random forests-based extreme learning machine ensemble for multi-regime time series prediction. Expert Systems with Applications, 83, 164–176. https://doi.org/10.1016/j.eswa.2017.04.013
18. Madani, S. S., et al. (2025). Advances in battery modeling and management systems: A comprehensive review of techniques, challenges, and future perspectives. Batteries, 11(11), Article 426. https://doi.org/10.3390/batteries11110426
19. Muratori, M., et al. (2021). The rise of electric vehicles—2020 status and future expectations. Progress in Energy, 3(2), Article 022002. https://doi.org/10.1088/2516-1083/abe0ad
20. Nerli, P., Andewale, B. A., Potdar, S., Sarsatti, S., & Badiger, V. (2025). Resource allocation optimization of smart city based on different ML models. In 2025 3rd International Conference on Smart Systems for Applications in Electrical Sciences (ICSSES) (pp. 1–6). IEEE. https://doi.org/10.1109/ICSSES64899.2025.11009895
21. Olugbade, S., Ojo, S., Imoize, A. L., Isabona, J., & Alaba, M. O. (2022). A review of artificial intelligence and machine learning for incident detectors in road transport systems. Mathematical and Computational Applications, 27(5), Article 77. https://doi.org/10.3390/mca27050077
22. Ou, S., Zhang, S., Lin, Z., & Davis, S. (2023). A method for determining optimal electric range by considering electric vehicle lightweighting on perceived ownership cost. Journal of Cleaner Production, 385, Article 135606. https://doi.org/10.1016/j.jclepro.2022.135606
23. Pathak, S. K., Sood, V., Singh, Y., & Channiwala, S. A. (2016). Real world vehicle emissions: Their correlation with driving parameters. Transportation Research Part D: Transport and Environment, 44, 157–176. https://doi.org/10.1016/j.trd.2016.02.001
24. Razzaq, K., & Shah, M. (2025). Machine learning and deep learning paradigms: From techniques to practical applications and research frontiers. Computers, 14(3), Article 93. https://doi.org/10.3390/computers14030093
25. Salman, H. A., Kalakech, A., & Steiti, A. (2024). Random forest algorithm overview. Babylonian Journal of Machine Learning, 2024, 69–79. https://doi.org/10.58496/BJML/2024/007
26. Shi, X., Pan, J., Wang, H., & Cai, H. (2019). Battery electric vehicles: What is the minimum range required? Energy, 166, 352–358. https://doi.org/10.1016/j.energy.2018.10.056
27. Szczepanek, R. (2022). Daily streamflow forecasting in mountainous catchment using XGBoost, LightGBM and CatBoost. Hydrology, 9(12), Article 226. https://doi.org/10.3390/hydrology9120226
28. Vaddy, R. K. (2023). AI and ML for transportation route optimization. International Transactions on Machine Learning, 5(5), 1–19.
29. Varga, B. O., Sagoian, A., & Mariasiu, F. (2019). Prediction of electric vehicle range: A comprehensive review of current issues and challenges. Energies, 12(5), Article 946. https://doi.org/10.3390/en12050946
30. Yang, G. R., & Wang, X.-J. (2020). Artificial neural networks for neuroscientists: A primer. Neuron, 107(6), 1048–1070. https://doi.org/10.1016/j.neuron.2020.09.005
31. Zhang, C., Zhang, Y., Shi, X., Almpanidis, G., Fan, G., & Shen, X. (2019). On incremental learning for gradient boosting decision trees. Neural Processing Letters, 50(1), 957–987. https://doi.org/10.1007/s11063-018-9908-0
32. Zhu, C., et al. (2022). Internal heating techniques for lithium-ion batteries at cold climates: An overview for automotive applications. IEEE Transactions on Transportation Electrification, 9(4), 5012–5027. https://doi.org/10.1109/TTE.2022.3208186