Skip to Main content Skip to Navigation

Spatio-temporal Probabilistic Short-term Forecasting on Urban Networks

Cyril Furtlehner 1 Jean-Marc Lasgouttes 2 Alessandro Attanasi 3 Lorenzo Meschini 3 Marco Pezzulla 3 
1 TAU - TAckling the Underspecified
Inria Saclay - Ile de France, LISN - Laboratoire Interdisciplinaire des Sciences du Numérique
Abstract : The probabilistic forecasting method described in this study is designed to leverage spatial and temporal dependency of urban traffic networks in order to provide accurate predictions for a horizon of up to several 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 entire network in one pass with an execution time that scales linearly with the size of the network. The method consists in learning a sparse Gaussian copula of traffic variables, compatible with the Gaussian belief propagation algorithm. The model is trained automatically from an historical dataset through an iterative proportional scaling procedure that is well suited to compatibility constraints. It is tested on three different datasets of increasing sizes ranging from 250 to 2000 detectors corresponding to flow and/or speed and occupancy measurements. The results show a very good ability to predict flow variables and reasonably good performances on speed or occupancy variables. Some understanding of the observed performances is given by a careful analysis of the model, making it to some degree possible to disentangle modelling bias from the intrinsic noise of the traffic phenomena and its measurement process.
Complete list of metadata
Contributor : Jean-Marc Lasgouttes Connect in order to contact the contributor
Submitted on : Friday, July 16, 2021 - 12:34:01 PM
Last modification on : Thursday, June 9, 2022 - 3:41:07 AM


Files produced by the author(s)


  • HAL Id : hal-01964270, version 2


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 -Île de France; Inria de Paris; PTV-SISTeMA. 2019, pp.30. ⟨hal-01964270v2⟩



Record views


Files downloads