Nonseparable dynamic nearest neighbor Gaussian process models for large spatio-temporal data with an application to particulate matter analysis

Abhirup Datta, Sudipto Banerjee, Andrew O. Finley, Nicholas A.S. Hamm, Martijn Schaap

Research output: Contribution to journalArticlepeer-review

Abstract

Particulate matter (PM) is a class of malicious environmental pollutants known to be detrimental to human health. Regulatory efforts aimed at curbing PM levels in different countries often require high resolution space–time maps that can identify red-flag regions exceeding statutory concentration limits. Continuous spatio-temporal Gaussian Process (GP) models can deliver maps depicting predicted PM levels and quantify predictive uncertainty. However, GP-based approaches are usually thwarted by computational challenges posed by large datasets. We construct a novel class of scalable Dynamic Nearest Neighbor Gaussian Process (DNNGP) models that can provide a sparse approximation to any spatio-temporal GP (e.g., with nonseparable covariance structures). The DNNGP we develop here can be used as a sparsity-inducing prior for spatio-temporal random effects in any Bayesian hierarchical model to deliver full posterior inference. Storage and memory requirements for a DNNGP model are linear in the size of the dataset, thereby delivering massive scalability without sacrificing inferential richness. Extensive numerical studies reveal that the DNNGP provides substantially superior approximations to the underlying process than low-rank approximations. Finally, we use the DNNGP to analyze a massive air quality dataset to substantially improve predictions of PM levels across Europe in conjunction with the LOTOS-EUROS chemistry transport models (CTMs).

Original languageEnglish (US)
Pages (from-to)1286-1316
Number of pages31
JournalAnnals of Applied Statistics
Volume10
Issue number3
DOIs
StatePublished - Sep 2016

Keywords

  • Bayesian inference
  • Environmental pollutants
  • Markov chain Monte Carlo
  • Nearest neighbors
  • Nonseparable spatio-temporal models
  • Scalable Gaussian process

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation
  • Statistics, Probability and Uncertainty

Fingerprint Dive into the research topics of 'Nonseparable dynamic nearest neighbor Gaussian process models for large spatio-temporal data with an application to particulate matter analysis'. Together they form a unique fingerprint.

Cite this