Urban traffic volume forecasting using machine learning and neural networks

Abstract

To build sustainable cities, it is critical to be able to predict traffic volume and to manage and control it effectively, especially in large cities. This study aims to determine whether the number of vehicles on the road in Istanbul, the world's most congested city, can be predicted using meteorological and traffic-related variables. The data used in this study were obtained from IBB Open Data Portal and the Weather Underground platforms. Machine learning techniques and Artificial Neural Networks were used in the research, and R programming language was used for data analysis. As a result of the research, the models with the highest prediction accuracy were XGBoost, Artificial Neural Network, and Ridge Regression, respectively. The most important variables affecting traffic volume are average speed, maximum speed, minimum speed, weekends, and temperature, respectively. The study also found a positive relationship between traffic volume and temperature, while traffic volume decreased significantly on weekends. The research results can guide vehicle drivers on what time of day and route to use and to pedestrians on whether they should use their personal vehicles or public transportation. On the other hand, local governments can manage increases in traffic volume at certain hours by evaluating whether the existing road infrastructure is sufficient for the observed daily traffic volume and peak-hour demand, thus contributing to sustainable urban life with less air pollution, less stress, fewer traffic violations, and fewer accidents.

Keywords

• Urban traffic volume
• traffic forecasting
• machine learning
• artificial neural networks
• meteorological factors

Supporting Institution

This study was supported by the Scientific Research Projects Coordination Unit of Gebze Technical University within the scope of the Research Universities Support Program (ADEP). Project Number: 2024-A-113-13.

Project Number

2024-A-113-13

Ethical Statement

No Ethics Committee approval is required; secondary data has been used.

Kentsel trafik hacminin makine öğrenmesi ve yapay sinir ağları kullanılarak tahmin edilmesi

Abstract

Sürdürülebilir kentlerin oluşturulabilmesi için özellikle büyükşehirlerde trafik hacminin belirlenmesi ile etkin bir şekilde yönetilmesi ve kontrol edilmesi kritik öneme sahiptir. Bu çalışma, dünyanın en yüksek trafik yoğunluğuna sahip kentlerinden biri olan İstanbul'da karayolu üzerindeki araç sayısının meteorolojik ve trafikle ilişkili değişkenler kullanılarak tahmin edilip edilemeyeceğini belirlemeyi amaçlamaktadır. Araştırmada kullanılan veriler, İstanbul Büyükşehir Belediyesi (İBB) Açık Veri Portalı ile Weather Underground platformlarından elde edilmiştir. Araştırmada makine öğrenmesi algoritmaları ve Yapay Sinir Ağları (YSA) yöntemi kullanılmış; veri analizleri R programlama dili aracılığıyla gerçekleştirilmiştir. Araştırma sonuçlarına göre, en yüksek tahmin performansına sahip modeller sırasıyla XGBoost, Yapay Sinir Ağları ve Ridge Regresyonu olmuştur. Trafik hacmini etkileyen en önemli değişkenlerin ise sırasıyla ortalama hız, maksimum hız, minimum hız, tatil günleri (hafta sonları) ve sıcaklık olduğu belirlenmiştir. Ayrıca, trafik hacmi ile sıcaklık arasında pozitif yönlü bir ilişki olduğu, buna karşın hafta sonlarında trafik hacminin anlamlı düzeyde azaldığı tespit edilmiştir. Araştırma bulgularının, sürücülere günün hangi saatlerinde ve hangi güzergâhlarda seyahat etmelerinin daha uygun olacağı konusunda yol gösterici olabileceği, ayrıca yayaların kişisel araç kullanımı ile toplu taşıma arasında tercih yapmalarına katkı sağlayabileceği değerlendirilmektedir. Bunun yanı sıra, yerel yönetimler mevcut yol altyapısının günlük trafik hacmi ve pik saatlerdeki talebi karşılayıp karşılamadığını değerlendirerek belirli saatlerde yaşanan trafik yoğunluğunu daha etkin biçimde yönetebilir. Bu doğrultuda çalışma; hava kirliliğinin azaltılması, stres düzeyinin düşürülmesi, trafik ihlallerinin ve trafik kazalarının önlenmesi yoluyla sürdürülebilir kentsel yaşama katkı sunabilecek niteliktedir.

Keywords

• Kentsel trafik hacmi
• trafik tahmini
• makine öğrenmesi
• yapay sinir ağları
• meteorolojik faktörler

Supporting Institution

Bu çalışma, Araştırma Üniversiteleri Destek Programı (ADEP) kapsamında Gebze Teknik Üniversitesi Bilimsel Araştırma Projeleri Koordinatörlüğü tarafından desteklenmiştir. Proje Numarası: 2024-A-113-13.

Project Number

2024-A-113-13

Ethical Statement

Etik Kurul belgesi gerektirmemektedir, ikincil veriler kullanılmıştır.

References

1. Abdel-Aty, M., Ekram, A.-A., Huang, H., & Choi, K. (2011). A study on crashes related to visibility obstruction due to fog and smoke. Accident Analysis & Prevention, 43(5), 1730-1737. https://doi.org/10.1016/j.aap.2011.04.003
2. Darcin, A., Virginia, S. & Alexander, S. (2011). Impacts of weather on traffic flow characteristics of urban freeways in Istanbul. Procedia - Social and Behavioral Sciences. 16, 89-99. https://doi.org/10.1016/j.sbspro.2011.04.43
3. Andrey, J., Hambly, D., Mills, B., & Afrin, S. (2013). Insights into driver adaptation to inclement weather in Canada. Journal of Transport Geography, 28, 192-203. https://doi.org/10.1016/j.jtrangeo.2012.08.014
4. Hermans, E., Brijs, T., Stiers, T., & Offermans, C. (2006). The impact of weather conditions on road safety investigated on an hourly basis. Transportation Research Board. Retrieved from: http://pubsindex.trb.org/document/view/default.asp?record=776722
5. Cools, M., Moons, E., & Wets, G. (2007). Investigating the effect of holidays on daily traffic counts: A time series approach. Transportation Research Record, 2019(1), 22–31. https://doi.org/10.3141/2019-04
6. Cools, M., Moons, E., & Wets, G. (2010). Assessing the impact of weather on traffic intensity. Weather Climate and Society, 2(1), 60-68. https://doi.org/10.1175/2009WCAS1014.1
7. Dhaliwal, S. S., Nahid, A. A. & Abbas, R. (2018). Effective intrusion detection system using XGBoost. Information, 9(7), 149. https://doi.org/10.3390/info9070149
8. Das, A. & Ghasemzadeh, A. (2018). Analyzing the effect of fog weather conditions on driver lane-keeping performance using the SHRP2 naturalistic driving study data. Journal of Safety Research. 68. https://doi.org/10.1016/j.jsr.2018.12.015

9. Datla, S., & Sharma, S. (2008). Impact of cold and snow on temporal and spatial variations of highway traffic volumes. Journal of Transport Geography, 16(5), 358-372. https://doi.org/10.1016/j.jtrangeo.2007.12.003
10. Dey, K. C., Mishra, A., & Chowdhury, M. (2015). Potential of Intelligent transportation systems in mitigating adverse weather impacts on road mobility: a review. IEEE Transactions on Intelligent Transportation Systems, 16(3), 1107-1119. https://doi.org/10.1109/TITS.2014.2371455
11. Dia, H. (2001). An object- oriented neural network approach to short- term traffic forecasting. European Journal of Operational Research, 131(2), 253-261. https://doi.org/10.1016/S0377-2217(00)00125-9
12. Dunne, S., & Ghosh, B. (2013). Weather adaptive traffic prediction using Neurowavelet Models. IEEE Transactions on Intelligent Transportation Systems, 14(1), 370-379. https://doi.org/10.1109/TITS.2012.2225049
13. Florio, L., & Mussone, L. (1996). Neural- network models for classification and forecasting of freeway traffic flow stability. Control Engineering Practice, 4(2), 153-164. https://doi.org/10.1016/0967-0661(95)00221-9
14. Gupta, N. (2013). Artificial neural network. Network and Complex Systems, 3(1), 24-28.
15. Gürsakal, N. (2018). Makine Öğrenmesi. Bursa: Dora Yayıncılık
16. Haykin, S. (1998). Neural Networks A Comprehensive Foundation (Second Edition). Pearson Education.
17. Karabulut, F. Y. (2015). Estimation of traffic density based on past density information for adaptive traffic management [Master Thesis]. Dokuz Eylül University, Graduate School of Natural and Applied Sciences, İzmir.
18. General Directorate of Highways. (2023). Road statistics. Retrieved from: https://www.kgm.gov.tr/Sayfalar/KGM/SiteTr/Root/default.aspx. (Accessed at: 24.01.2023)
19. Keay, K., & Simmonds, I. (2005). The association of rainfall and other weather variables with road traffic volume in Melbourne, Australia. Accident Analysis and Prevention, 37(1), 109-124. https://doi.org/10.1016/j.aap.2004.07.005
20. Kilpelainen, M., & Summala, H. (2007). Effects of weather and weather forecasts on driver behaviour. Transportation Research Part F-Traffic Psychology and Behaviour, 10(4), 288-299. https://doi.org/10.1016/j.trf.2006.11.002
21. Kopal, B. (2011). Boğaziçi köprüsü üzerindeki trafik sıkışıklığının hız yönetimi yöntemiyle azaltılması [Yüksek Lisans Tezi]. Bahçeşehir Üniversitesi Fen Bilimleri Fakültesi, İstanbul.
22. Kumar, K., Kumar, M., & Das, P. (2024). Traffic congestion forecasting using multilayered deep neural network. Transportation Letters, 16(6), 516-526.https://doi.org/10.1080/19427867.2023.2207278
23. Kyte, M., Khatib, Z., Shannon, P., & Kitchener, F. (2001). Effect of weather on free-flow speed. Transportation Research Record, 1776(1), 60-68. https://doi.org/10.3141/1776-08
24. INRIX (2024). Global traffic scorecard. Retrieved from: https://inrix.com/scorecard/ (Accessed at: 01.04.2025)
25. Levine, N., Kim, K. E., & Nitz, L. H. (1995). Daily fluctuations in honolulu motor vehicle accidents. Accident Analysis and Prevention, 27(6), 785-796. https://doi.org/10.1016/0001-4575(95)00038-0
26. Liu, F., Ma, X., An, X., & Liang, G. (2020). Urban traffic flow prediction model with CPSO/SSVM algorithm under the edge computing framework. Wireless Communications and Mobile Computing, 2020(1), 8871998. https://doi.org/10.1155/2020/8871998
27. Liu, A., Soneja, S. I., Jiang, C., Huang, C., Kerns, T., Beck, K., Mitchell, C., & Sapkota, A. (2017). Frequency of extreme weather events and increased risk of motor vehicle collision in Maryland. Science of The Total Environment, 580, 550-555. https://doi.org/10.1016/j.scitotenv.2016.11.211
28. Maind, S. B., & Wankar, P. (2014). Research paper on basic of artificial neural network. International Journal on Recent and Innovation Trends in Computing and Communication, 2(1), 96-100.
29. Medina-Salgado, B., Sánchez-DelaCruz, E., Pozos-Parra, P., & Sierra, J. E. (2022). Urban traffic flow prediction techniques: A review. Sustainable Computing: Informatics and Systems, 35, 100739. https://doi.org/10.1016/j.suscom.2022.100739
30. Menguc, K., Aydin, N., & Yilmaz, A. (2023). A data driven approach to forecasting traffic speed classes using extreme gradient boosting algorithm and graph theory. Physica A: Statistical Mechanics and its Applications, 620, 128738. https://doi.org/10.1016/j.physa.2023.128738
31. Öztemel, E. (2016). Yapay Sinir Ağları (4. bs). İstanbul: Papatya Yayıncılık Eğitim.
32. Öztürk, K., & Şahin, M. E. (2018). Yapay sinir ağları ve yapay zekâ’ya genel bir bakış. Takvim-I Vekayi, 6(2), 25-36. Retrieved from: https://izlik.org/JA73RE73XY
33. Shahid, N., Shah, M. A., Khan, A., Maple, C., & Jeon, G. (2021). Towards greener smart cities and road traffic forecasting using air pollution data. Sustainable Cities and Society, 72, 103062. https://doi.org/10.1016/j.scs.2021.103062
34. Shankar, V. N., Chayanan, S., Sittikariya, S., Shyu, M.-B., Juvva, N. K., & Milton, J. C. (2004). Marginal impacts of design, traffic, weather, and related interactions on roadside crashes. Transportation Research Record, 1897(1), 156-163. https://doi.org/10.3141/1897-20
35. Singh, S., Singh, J., Goyal, S. B., Sehra, S. S., Ali, F., Alkhafaji, M. A., & Singh, R. (2023). A novel framework to avoid traffic congestion and air pollution for sustainable development of smart cities. Sustainable Energy Technologies and Assessments, 56, 103125. https://doi.org/10.1016/j.seta.2023.103125
36. Stipancic, J., Miranda-Moreno, L., & Saunier, N. (2017). Impact of congestion and traffic flow on crash frequency and severity: Application of smartphone-collected GPS travel data. Transportation Research Record, 2659(1), 43–54. https://doi.org/10.3141/2659-05
37. Tektaş, M., Akbaş, A., & Topuz, V. (2002). Yapay Zeka Tekniklerinin trafik kontrolünde kullanılması üzerine bir inceleme. Uluslararası Trafik ve Yol Güvenliği Kongresi ve Fuarı.
38. TÜİK. (2023). Retrieved from: http://www.tuik.gov.tr/UstMenu.do?metod=istgosterge. (Accessed at: 24.01.2023)
39. Unrau, D., & Andrey, J. (2006). Driver response to rainfall on urban expressways. Transportation research record, 1980(1), 24-30. https://doi.org/10.1177/0361198106198000105
40. Yan, X., Li, X., Liu, Y., & Zhao, J. (2014). Effects of foggy conditions on drivers’ speed control behaviors at different risk levels. Safety Science, 68, 275-287. https://doi.org/10.1016/j.ssci.2014.04.013
41. Yayla, N. (2004). Karayolu Mühendisliği. İstanbul: Birsen Yayınevi.
42. Yildirim, U., & Özcan, U. (2015). Ankara şehiriçi trafik kazalarının analizi: Bir yapay sinir ağı modeli. Gazi Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 17(1), 35-63. Retrieved from: https://izlik.org/JA36KA97DB