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

TL;DR

This paper introduces a Bayesian hierarchical spatio-temporal model for high-resolution, short-term precipitation forecasting, integrating radar and gauge data, and employing an ensemble Kalman smoother within a Gibbs sampler for efficient inference.

Contribution

The paper develops a novel Bayesian inference scheme for a complex spatio-temporal precipitation model, enabling uncertainty quantification and efficient computation with large datasets.

Findings

Effective probabilistic precipitation forecasts demonstrated on real data

The ensemble Kalman smoother within Gibbs sampling provides computationally feasible inference

Model captures uncertainty in both parameters and forecasts

Abstract

With extreme weather events becoming more common, the risk posed by surface water flooding is ever increasing. In this work we propose a model, and associated Bayesian inference scheme, for generating probabilistic (high-resolution short-term) forecasts of localised precipitation. The parametrisation of our underlying hierarchical dynamic spatio-temporal model is motivated by a forward-time, centred-space finite difference solution to a collection of stochastic partial differential equations, where the main driving forces are advection and diffusion. Observations from both weather radar and ground based rain gauges provide information from which we can learn about the likely values of the (latent) precipitation field in addition to other unknown model parameters. Working in the Bayesian paradigm provides a coherent framework for capturing uncertainty both in the underlying model parameters and also in our forecasts. Further, appealing to simulation based (MCMC) sampling yields a straightforward solution to handling zeros, treated as censored observations, via data augmentation. Both the underlying state and the observations are of moderately large dimension ($\mathcal{O}(10^4)$ and $\mathcal{O}(10^3)$ respectively) and this renders standard inference approaches computationally infeasible. Our solution is to embed the ensemble Kalman smoother within a Gibbs sampling scheme to facilitate approximate Bayesian inference in reasonable time. Both the methodology and the effectiveness of our posterior sampling scheme are demonstrated via simulation studies and also by a case study of real data from the Urban Observatory project based in Newcastle upon Tyne, UK.