Boudabbous, Emna, Karaa, Mohamed, Sboui, Lokman, Montecinos, Julio et Alam, Omar.
2026.
« Scalable transit delay prediction at city scale: A systematic approach with multi-resolution feature engineering and deep learning ».
Journal of Systems Architecture, vol. 176.
Prévisualisation |
PDF
Sboui-L-2026-33721.pdf - Version publiée Licence d'utilisation : Creative Commons CC BY. Télécharger (2MB) | Prévisualisation |
Résumé
Urban bus transit agencies need reliable, network-wide delay predictions to provide accurate arrival information to passengers and support real-time operational control. Accurate predictions help passengers plan their trips, reduce waiting time, and allow operations staff to adjust headways, dispatch additional vehicles, and manage disruptions. Although real-time feeds such as GTFS-RT are now widely available, most existing delay prediction systems handle only a few routes, rely on hand-crafted features, and offer little guidance on designing a scalable, reusable architecture. We present a city-scale prediction pipeline that combines multi-resolution feature engineering, dimensionality reduction, and deep learning. The framework systematically generates spatiotemporal features by exploring aggregation combinations over spatial regions (using hexagonal hierarchical indexing), routes, segments, and temporal patterns, then compresses them using Adaptive PCA while preserving 95 % of the variance. To avoid the “giant cluster” problem that occurs when dense urban areas fall into a single spatial region, we introduce a hybrid clustering method that combines geographic and network topology information to yield balanced route clusters and enable efficient distributed training. We compare five model architectures on six months of bus operations from the Société de transport de Montréal (STM) network in Montréal. A global LSTM with cluster-aware features achieves the best trade-off between accuracy and efficiency ( at the elementary level), outperforming XGBoost by 9.3 %, xLSTM by 5.3 %, and Autoformer by 43 % in terms of , while achieving comparable accuracy to PatchTST () with fewer parameters. LSTM’s compact architecture (31,000 parameters) effectively captures short-term temporal dependencies in the compressed feature space, making it more suitable than transformer models, which are overparameterized for this task. We also report multi-level evaluation at the elementary segment, segment, and trip level using walk-forward validation and latency analysis, showing that the proposed pipeline is suitable for real-time, city-scale deployment and can be reused for other networks with limited adaptation.
| Type de document: | Article publié dans une revue, révisé par les pairs |
|---|---|
| Chercheur(-euse): | Chercheur(-euse) Sboui, Lokman Montecinos, Julio |
| Affiliation: | Génie des systèmes, Génie des systèmes |
| Date de dépôt: | 12 mai 2026 14:39 |
| Dernière modification: | 22 mai 2026 22:31 |
| URI: | https://espace2.etsmtl.ca/id/eprint/33721 |
Actions (Authentification requise)
 |
Dernière vérification avant le dépôt |