Spatio-temporal Probabilistic Short-term Forecasting on Urban Networks

Cyril Furtlehner 1, 2 Jean-Marc Lasgouttes 3 Alessandro Attanasi 4 Lorenzo Meschini 4 Marco Pezzulla 4
2 TAU - TAckling the Underspecified
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : The probabilistic forecasting method described in this work is designed to leverage spatial and temporal dependency of urban traffic networks in order to provide accurate predictions for an horizon up to a few hours. By design it can deal with missing data both for training and running the model. It is able to forecast the state of the whole network in one pass with an execution time scaling linearly with the size of the network. The method consists in two learn a sparse Gaussian Copula of traffic variables, compatible with the Gaussian belief propagation algorithm. The model is learned automatically from an historical dataset through an iterative proportional scaling procedure well suited to impose this compatibility constraint. It is tested on three different datasets of increasing sizes ranging from 250 to 2000 detectors corresponding to flow or/and speed and occupancy measurements. The results show very good ability to predict flow variables and a reasonably good performance on speed or occupancy variables. Some element of understanding of the observed performance are given by a careful analysis of the model allowing to some extend to disentangle modelling bias from intrinsic noise of the traffic phenomena and its measurement process.
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download

https://hal.inria.fr/hal-01964270
Contributor : Cyril Furtlehner <>
Submitted on : Friday, December 21, 2018 - 7:19:40 PM
Last modification on : Tuesday, February 12, 2019 - 12:54:05 PM
Long-term archiving on : Friday, March 22, 2019 - 6:19:52 PM

File

RR-9236.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01964270, version 1

Citation

Cyril Furtlehner, Jean-Marc Lasgouttes, Alessandro Attanasi, Lorenzo Meschini, Marco Pezzulla. Spatio-temporal Probabilistic Short-term Forecasting on Urban Networks. [Research Report] RR-9236, INRIA Saclay, équipe TAU; INRIA de Paris, équipe RITS; PTV-SISTeMA. 2018. ⟨hal-01964270⟩

Share

Metrics

Record views

134

Files downloads

404