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

Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02297513
Contributor : Edouard Delasalles <>
Submitted on : Friday, September 27, 2019 - 10:09:49 AM
Last modification on : Tuesday, October 1, 2019 - 1:20:28 AM

File

stnn.pdf
Files produced by the author(s)

Identifiers

Citation

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⟩

Share

Metrics

Record views

35

Files downloads

29