Improving public transport prediction accuracy through multi-source data integration

A case study of Ljubljana

Autores/as

DOI:

https://doi.org/10.66838/sauc.6424

Palabras clave:

Public transport, Congestion, Travel time, Machine learning, LOOCV

Resumen

This study proposes a data acquisition, preprocessing and machine learning pipeline to enhance the accuracy of travel time estimates for the public bus network in Ljubljana, Slovenia. Existing prediction services often rely on vehicle location and may insufficiently capture dynamic congestion and contextual conditions. Using data from five Ljubljana Passenger Transport (LPP) routes, we evaluate LPP and Google Routes estimates against observed travel times. We develop a multisource model combining real-time variables with contextual predictors, including bus line, time of day, day type, and weather. The approach demonstrates how multisource integration of local transit feeds, external routing, and environmental indicators can improve prediction accuracy, reliability, and overall performance.

Descargas

Los datos de descargas todavía no están disponibles.

Estadísticas globales ℹ️

Totales acumulados desde su publicación
0
Visualizaciones
0
Descargas
0
Total

Citas

Bachu, A. K., Reddy, K. K., & Vanajakshi, L. (2021). Bus travel time prediction using support vector machines for high variance conditions. Transport, 36(3), 221–234. https://doi.org/10.3846/transport.2021.15220

Bole, D. (2004). Geografija javnega potniškega prometa na primeru Ljubljane. Geografski vestnik, 76(2), 21–32.

Chen, R., Zhang, J., Xu, X., Han, T.-D., & He, M. (2026). Comparative analysis and case study of travel time reliability measures for public usage of transportation information. Journal of Transport Geography. https://doi.org/10.1016/j.jtrangeo.2026.103928

Dunne, L., Rocco Di Torrepadula, F., Di Martino, S., McArdle, G., & Nardone, D. (2023). Bus journey time prediction with machine learning: An empirical experience in two cities. In M. A. Mostafavi & G. Del Mondo (Eds.), Web and wireless geographical information systems (pp. 105–120). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-34612-5_7

Google. (2024, October 16). GTFS Realtime Overview. Google for Developers. https://developers.google.com/transit/gtfs-realtime

Google. (2026). Routes API. Google for Developers. https://developers.google.com/maps/documentation/routes

Gössling, S., Neger, C., Steiger, R., & Bell, R. (2023). Weather, climate change, and transport: A review. Natural Hazards, 118, 1341–1360. https://doi.org/10.1007/s11069-023-06054-2

Hansson, J., Pettersson-Löfstedt, F., Svensson, H., & Wretstrand, A. (2022). Effects of rural bus stops on travel time and reliability. Public Transport, 14, 683–704. https://doi.org/10.1007/s12469-021-00281-1

Henríquez-Jara, B., Arriagada, J., & Tirachini, A. (2025). Impact of real-time information on passenger satisfaction across varying public transport quality levels in 13 Chilean cities. Transportation Research Part A: Policy and Practice, 200. https://doi.org/10.1016/j.tra.2025.104408

Kandiri, A., Ghiasi, R., Nogal, M., & Teixeira, R. (2024). Travel time prediction for an intelligent transportation system based on a data-driven feature selection method considering temporal correlation. Transportation Engineering, 18, Article 100272. https://doi.org/10.1016/j.treng.2024.100272

Lau, J. (2020, September 3). Google Maps 101: How AI helps predict traffic and determine routes. The Keyword. https://blog.google/products-and-platforms/products/maps/google-maps-101-how-ai-helps-predict-traffic-and-determine-routes/

Liu, L., Porr, A., & Miller, H.J. (2023). Realizable accessibility: Evaluating the reliability of public transit accessibility using high-resolution real-time data. Journal of Geographical Systems, 25(3), 429–451. https://doi.org/10.1007/s10109-022-00382-w

Ljubljanski potniški promet. (2025). Shema dnevnih linij LPP: Mestni javni linijski prevoz in integrirane potniške linije [Public transport network map].

Ljubljanski potniški promet. (2026). LPP API documentation. https://data.lpp.si/doc/

Mestna občina Ljubljana. (2022). Lokalni energetski koncept Mestne občine Ljubljana za obdobje od 2022 do 2030: I. del – Analiza stanja.

Open-Meteo. (2026). Weather Forecast API. https://open-meteo.com/en/docs

Parslov, A., Petersen, N.C., & Rodrigues, F. (2023). Short-term bus travel time prediction for transfer synchronization with intelligent uncertainty handling. Expert Systems with Applications, 232, 120751. https://doi.org/10.1016/j.eswa.2023.120751

Rashvand, N., Hosseini, S., Azarbayjani, M., & Tabkhi, H. (2024). Real-time bus arrival prediction: A deep learning approach for enhanced urban mobility. In Proceedings of the 13th International Conference on Operations Research and Enterprise Systems (pp. 123–132). SCITEPRESS. https://doi.org/10.5220/0012365500003639

Schmitt, A. U., Burgemeister, F., Dorff, H., Finn, T., Hansen, A., Kirsch, B., Lange, I., Radtke, J., & Ament, F. (2023). Assessing the weather conditions for urban cyclists by spatially dense measurements with an agent-based approach. Meteorological Applications, 30(6), e2164. https://doi.org/10.1002/met.2164

scikit-learn developers. (n.d.). sklearn. scikit-learn. Retrieved August 28, 2026, from https://scikit-learn.org/stable/api/sklearn.html

Serin, F., Alisan, Y., & Erturkler, M. (2022). Predicting bus travel time using machine learning methods with three-layer architecture. Measurement, 198, 111403. https://doi.org/10.1016/j.measurement.2022.111403

Slovenian Environment Agency (ARSO). (2025). Ljubljana Bežigrad: Climate statistics and normals 1991–2020.

SURS, Statistical Office of the Republic of Slovenia. (2026). Selected data on municipalities, Slovenia, annually. SiStat Database. https://pxweb.stat.si/SiStatData/pxweb/en/Data/Data/2640010S.px/

Trček, I. S., & Rijavec, R. (2026). Strategic evaluation of cycling infrastructure in emerging contexts: A case study of high-capacity corridors in Ljubljana, Slovenia. European Transport Research Review, 18, Article 67. https://doi.org/10.1186/s12544-026-00833-1

van Ardenne, M. T., Cebecauer, M., Cats, O., & Ma, Z. (2025). Personalised passenger information systems in public transport: A review and a 5-level personalisation taxonomy. Transport Reviews, 45(6), 1016–1047.

Xu, H., & Ying, J. (2017). Bus arrival time prediction with real-time and historic data. Cluster Computing, 20(4), 3099–3106. https://doi.org/10.1007/s10586-017-1006-1

Yu, B., Wang, H., Shan, W., & Yao, B. (2018). Prediction of bus travel time using random forests based on near neighbors. Computer-Aided Civil and Infrastructure Engineering, 33(4), 333–350.

Descargas

Publicado

2026-10-23

Cómo citar

Medvedec, R., Verovsek, S., & Moškon, M. (2026). Improving public transport prediction accuracy through multi-source data integration: A case study of Ljubljana. Street Art & Urban Creativity, 12(6), 65–82. https://doi.org/10.66838/sauc.6424

Número

Vol. 12 Núm. 6 (2026)

Sección

Artículos de investigación

Licencia

Derechos de autor 2026 Los autores/as conservan los derechos de autor y ceden a la revista el derecho de la primera publicación y el derecho de edición

Creative Commons License

Esta obra está bajo una licencia internacional Creative Commons Atribución-SinDerivadas 4.0.

Los autores/as que publiquen en esta revista aceptan las siguientes condiciones: 

  1. Los autores/as conservan los derechos de autor.
  2. Los autores/as ceden a la revista el derecho de la primera publicación. La revista también posee los derechos de edición.
  3.  Todos los contenidos publicados se regulan mediante una Licencia Atribución/Reconocimiento-SinDerivados 4.0 Internacional. Acceda a la versión informativa y texto legal de la licencia. En virtud de ello, se permite a terceros utilizar lo publicado siempre que mencionen la autoría del trabajo y a la primera publicación en esta revista. Si transforma el material, no podrá distribuir el trabajo modificado.
  4. Los autores/as pueden realizar otros acuerdos contractuales independientes y adicionales para la distribución no exclusiva de la versión del artículo publicado en esta revista (p. ej., incluirlo en un repositorio institucional o publicarlo en un libro) siempre que indiquen claramente que el trabajo se publicó por primera vez en esta revista.
  5. Se permite y recomienda a los autores/as a publicar su trabajo en Internet (por ejemplo en páginas institucionales o personales), una vez publicado en la revista y citando a la misma ya que puede conducir a intercambios productivos y a una mayor y más rápida difusión del trabajo publicado (vea The Effect of Open Access).