Scalable spatiotemporal prediction with Bayesian neural fields.

ABSTRACT: Spatiotemporal datasets, which consist of spatially-referenced time series, are ubiquitous in diverse applications, such as air pollution monitoring, disease tracking, and cloud-demand forecasting. As the scale of modern datasets increases, there is a growing need for statistical methods that are flexible enough to capture complex spatiotemporal dynamics and scalable enough to handle many observations. This article introduces the Bayesian Neural Field (BAYESNF), a domain-general statistical model that infers rich spatiotemporal probability distributions for data-analysis tasks including forecasting, interpolation, and variography. BAYESNF integrates a deep neural network architecture for high-capacity function estimation with hierarchical Bayesian inference for robust predictive uncertaint

SUBMITTER: Saad F 

PROVIDER: S-EPMC11390735 | biostudies-literature | 2024 Sep

REPOSITORIES: biostudies-literature