EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Climatology-Anchored Residual Learning for Spatio-Temporal Traffic Forecasting

Leonidas Boutsikaris, George Katrilakas, Athanasios Tsadiras, Symeon Samaras, Christina Topalidou

Computers · 2026-08-21 · 15 (8) · 548

DOI: 10.3390/computers15080548 ↗

At a glance

Journal article in Computers, published online on 2026-08-21. Written by Leonidas Boutsikaris and 4 co-authors. 26 references. The full text is freely available (open access, CC BY 4.0).

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Graph neural networks remain challenging to apply to traffic forecasting, often failing to consistently outperform simple baselines. We observe that the strongest baseline is regime-dependent: last-value persistence dominates at short horizons on smooth freeway data, while time-of-day climatology prevails at longer horizons and on bursty arterial networks. Rather than treating this as a limitation, we propose a learnable approach that automatically selects the optimal baseline. Our method anchors predictions to a learned, per-horizon convex blend of persistence and climatology, introducing only twelve scalar parameters. This learned anchor recovers whichever baseline is locally most effective, allowing the model to focus on capturing residual variations that neither baseline captures. We evaluate on six public benchmarks (METR-LA, PEMS-BAY, PEMS03/04/07/08) spanning traffic speed and flow data under standard 70/10/20 chronological splits with masked evaluation metrics and holiday-aware climatology. Our anchored temporal models consistently beat both baseline methods on the 12-step average across all datasets, and outperform at every horizon on five of the six benchmarks. When integrated into two strong architectures (STID and Graph WaveNet), the anchor yields substantial gains at long horizons where climatology is most informative. Notably, within our lightweight framework, learned spatial graph components do not improve accuracy and can slightly degrade performance, a finding we analyze and discuss.

Cite

APA

Boutsikaris, L., Katrilakas, G., Tsadiras, A., Samaras, S., & Topalidou, C. (2026). Climatology-Anchored Residual Learning for Spatio-Temporal Traffic Forecasting. Computers, 15(8), 548. https://doi.org/10.3390/computers15080548

Vancouver

Boutsikaris L, Katrilakas G, Tsadiras A, Samaras S, Topalidou C. Climatology-Anchored Residual Learning for Spatio-Temporal Traffic Forecasting. Computers. 2026;15(8):548. doi:10.3390/computers15080548

BibTeX
@article{Boutsikaris2026,
  author = {Boutsikaris, Leonidas and Katrilakas, George and Tsadiras, Athanasios and Samaras, Symeon and Topalidou, Christina},
  title = {Climatology-Anchored Residual Learning for Spatio-Temporal Traffic Forecasting},
  journal = {Computers},
  year = {2026},
  volume = {15},
  number = {8},
  pages = {548},
  doi = {10.3390/computers15080548}
}
Start for free →