EUVIMEDEUVIMED entdecken
Crossref

Scalable Dynamic Mixture Model with Full Covariance for Probabilistic Traffic Forecasting

Seongjin Choi, Nicolas Saunier, Vincent Zhihao Zheng, Martin Trépanier, Lijun Sun

Transportation Science · 2025-07 · 59 (4) · 708-720

DOI: 10.1287/trsc.2024.0547 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transportation Science, 2025-07. Verfasst von Seongjin Choi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 27 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep-learning-based multivariate and multistep-ahead traffic forecasting models are typically trained with the mean squared error (MSE) or mean absolute error (MAE) as the loss function in a sequence-to-sequence setting, simply assuming that the errors follow an independent and isotropic Gaussian or Laplacian distributions. However, such assumptions are often unrealistic for real-world traffic forecasting tasks, where the probabilistic distribution of spatiotemporal forecasting is very complex with strong concurrent correlations across both sensors and forecasting horizons in a time-varying manner. In this paper, we model the time-varying distribution for the matrix-variate error process as a dynamic mixture of zero-mean Gaussian distributions. To achieve efficiency, flexibility, and scalability, we parameterize each mixture component using a matrix normal distribution and allow the mixture weight to change and be predictable over time. The proposed method can be seamlessly integrated into existing deep-learning frameworks with only a few additional parameters to be learned. We evaluate the performance of the proposed method on a traffic speed forecasting task and find that our method not only improves model performance but also provides interpretable spatiotemporal correlation structures. History: This paper has been accepted for the Transportation Science Special Issue on Machine Learning Methods for Urban Passenger Mobility. Funding: This work was supported by Institut de Valorisation des Données (IVADO) through its Fundamental Research Funding Program.

Zitieren

APA

Choi, S., Saunier, N., Zheng, V. Z., Trépanier, M., & Sun, L. (2025). Scalable Dynamic Mixture Model with Full Covariance for Probabilistic Traffic Forecasting. Transportation Science, 59(4), 708-720. https://doi.org/10.1287/trsc.2024.0547

Vancouver

Choi S, Saunier N, Zheng VZ, Trépanier M, Sun L. Scalable Dynamic Mixture Model with Full Covariance for Probabilistic Traffic Forecasting. Transportation Science. 2025;59(4):708-720. doi:10.1287/trsc.2024.0547

BibTeX
@article{Choi2025,
  author = {Choi, Seongjin and Saunier, Nicolas and Zheng, Vincent Zhihao and Trépanier, Martin and Sun, Lijun},
  title = {Scalable Dynamic Mixture Model with Full Covariance for Probabilistic Traffic Forecasting},
  journal = {Transportation Science},
  year = {2025},
  volume = {59},
  number = {4},
  pages = {708--720},
  doi = {10.1287/trsc.2024.0547}
}
Kostenlos starten →