• Corpus ID: 54210362

An Additive Gaussian Process Approximation for Large Spatio-Temporal Data

  title={An Additive Gaussian Process Approximation for Large Spatio-Temporal Data},
  author={Pulong Ma and Bledar A. Konomi and Emily Lei Kang},
We propose a new additive spatio-temporal Gaussian process approximation to model complex dependence structures for large spatio-temporal data. The proposed approximation method incorporates a computational-complexity-reduction method and a separable covariant function, which can capture different scales of variation and spatio-temporal interactions. The first component is able to capture nonseparable variation while the second component captures the separable variation of all scales. The… 

Figures and Tables from this paper



Fused Gaussian Process for Very Large Spatial Data

A Gaussian process with additive components is proposed, with its covariance structure consisting of two components that is flexible without assuming a specific parametric covariance function but is able to achieve dimension reduction and robust against model misspecification.

Smoothed Full-Scale Approximation of Gaussian Process Models for Computation of Large Spatial Datasets

The proposed smoothed full-scale approximation (SFSA) method provides a unified view of approximation methods for GP models, grouping several existing computational methods for large spatial data sets into one common framework, allowing efficient algorithms that provide robust and accurate model inferences and predictions within a unified framework.

Gaussian predictive process models for large spatial data sets

This work achieves the flexibility to accommodate non‐stationary, non‐Gaussian, possibly multivariate, possibly spatiotemporal processes in the context of large data sets in the form of a computational template encompassing these diverse settings.

A Multiresolution Gaussian Process Model for the Analysis of Large Spatial Datasets

A multiresolution model to predict two-dimensional spatial fields based on irregularly spaced observations that gives a good approximation to standard covariance functions such as the Matérn and also has flexibility to fit more complicated shapes.


A novel class of scalable Dynamic Nearest Neighbor Gaussian Process (DNNGP) models that can provide a sparse approximation to any spatio-temporal GP, and is used 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.

Adaptive Gaussian predictive process models for large spatial datasets

This work views the knots as emerging from a point pattern and investigates how such adaptive specifications can yield more flexible hierarchical frameworks that lead to automated knot selection and substantial computational benefits.

A General Framework for Vecchia Approximations of Gaussian Processes

It is shown that the general Vecchia approach contains many popular existing GP approximations as special cases, allowing for comparisons among the different methods within a unified framework.

A full scale approximation of covariance functions for large spatial data sets

Summary.  Gaussian process models have been widely used in spatial statistics but face tremendous computational challenges for very large data sets. The model fitting and spatial prediction of such

Hierarchical Nearest-Neighbor Gaussian Process Models for Large Geostatistical Datasets

A class of highly scalable nearest-neighbor Gaussian process (NNGP) models to provide fully model-based inference for large geostatistical datasets are developed and it is established that the NNGP is a well-defined spatial process providing legitimate finite-dimensional Gaussian densities with sparse precision matrices.

A Multi-Resolution Approximation for Massive Spatial Datasets

A multi-resolution approximation (M-RA) of Gaussian processes observed at irregular locations in space is proposed, which can capture spatial structure from very fine to very large scales.