Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery

Résumé

We introduce a dynamical spatio-temporal model formalized as a recurrent neural network for forecasting time series of spatial processes, i.e. series of observations sharing temporal and spatial dependencies. The model learns these dependencies through a structured latent dynamical component, while a decoder predicts the observations from the latent representations. We consider several variants of this model, corresponding to different prior hypothesis about the spatial relations between the series. The model is evaluated and compared to state-of-the-art baselines, on a variety of forecasting problems representative of different application areas: epidemiology, geo-spatial statistics and car-traffic prediction. Besides these evaluations, we also describe experiments showing the ability of this approach to extract relevant spatial relations.
Fichier principal
Vignette du fichier
stnn.pdf (2.3 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02297513 , version 1 (26-09-2019)
hal-02297513 , version 2 (27-09-2019)

Identifiants

Citer

Ali Ziat, Edouard Delasalles, Ludovic Denoyer, Patrick Gallinari. Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery. 2017 IEEE International Conference on Data Mining (ICDM), Nov 2017, La Nouvelle Orléans, LA, United States. pp.705-714, ⟨10.1109/ICDM.2017.80⟩. ⟨hal-02297513v2⟩
738 Consultations
300 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More