RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting

by   Soumyasundar Pal, et al.

Spatio-temporal forecasting has numerous applications in analyzing wireless, traffic, and financial networks. Many classical statistical models often fall short in handling the complexity and high non-linearity present in time-series data. Recent advances in deep learning allow for better modelling of spatial and temporal dependencies. While most of these models focus on obtaining accurate point forecasts, they do not characterize the prediction uncertainty. In this work, we consider the time-series data as a random realization from a nonlinear state-space model and target Bayesian inference of the hidden states for probabilistic forecasting. We use particle flow as the tool for approximating the posterior distribution of the states, as it is shown to be highly effective in complex, high-dimensional settings. Thorough experimentation on several real world time-series datasets demonstrates that our approach provides better characterization of uncertainty while maintaining comparable accuracy to the state-of-the art point forecasting methods.


page 1

page 2

page 3

page 4


Clustering of Time Series Data with Prior Geographical Information

Time Series data are broadly studied in various domains of transportatio...

Stanza: A Nonlinear State Space Model for Probabilistic Inference in Non-Stationary Time Series

Time series with long-term structure arise in a variety of contexts and ...

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

We introduce a dynamical spatio-temporal model formalized as a recurrent...

Recurrent Flow Networks: A Recurrent Latent Variable Model for Spatio-Temporal Density Modelling

When modelling real-valued sequences, a typical approach in current RNN ...

Bayesian spatio-temporal model for high-resolution short-term forecasting of precipitation fields

With extreme weather events becoming more common, the risk posed by surf...

An Interpretable Probabilistic Autoregressive Neural Network Model for Time Series Forecasting

Forecasting time series data presents an emerging field of data science ...

A Probabilistic Time-Evolving Approach to Scanpath Prediction

Human visual attention is a complex phenomenon that has been studied for...