Nonseparable dynamic nearest neighbor Gaussian process models for large spatio-temporal data with an application to particulate matter analysis
Open Access
- 1 September 2016
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Applied Statistics
- Vol. 10 (3) , 1286-1316
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).Keywords
All Related Versions
This publication has 68 references indexed in Scilit:
- Estimation and Prediction in Spatial Models With Block Composite LikelihoodsJournal of Computational and Graphical Statistics, 2014
- Long-term air pollution exposure and cardio- respiratory mortality: a reviewEnvironmental Health, 2013
- Bayesian dynamic modeling for large space-time datasets using Gaussian predictive processesJournal of Geographical Systems, 2011
- Testing the capability of the chemistry transport model LOTOS-EUROS to forecast PM10 levels in the NetherlandsAtmospheric Environment, 2009
- Gaussian Predictive Process Models for Large Spatial Data SetsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2008
- A model inter-comparison study focussing on episodes with elevated PM10 concentrationsAtmospheric Environment, 2008
- The LOTOS EUROS model: description, validation and latest developmentsInternational Journal of Environment and Pollution, 2008
- Bayesian Measures of Model Complexity and FitJournal of the Royal Statistical Society Series B: Statistical Methodology, 2002
- Classes of Nonseparable, Spatio-Temporal Stationary Covariance FunctionsJournal of the American Statistical Association, 1999
- Estimation and Identification of Space-Time ARMAX Models in the Presence of Missing DataJournal of the American Statistical Association, 1986