Online Program Home
  My Program

Abstract Details

Activity Number: 303 - Big Data
Type: Contributed
Date/Time: Tuesday, August 1, 2017 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Computing
Abstract #322781
Title: Multi-Resolution Approximations of Gaussian Processes for Big Spatial Data
Author(s): Wenlong Gong*
Companies: Texas A&M University
Keywords: Basis functions ; Gaussian process ; Full-scale approximation ; Satellite data ; Sparse matrices

Remote-sensing instruments have enabled the collection of big spatial data over large domains such as entire continents or the globe. Basis-function representations are well suited to big spatial data, as they can enable fast computations for large datasets and they provide flexibility to deal with the complicated dependence structures often encountered over large domains. We discuss a multi-resolution approximation (MRA) that uses basis functions at multiple resolutions to achieve fast inference and that can (approximately) represent any covariance structure. We present two versions of the MRA: The first version results in a multi-resolution taper that can deal with large datasets. The second version is based on a multi-resolution partitioning of the spatial domain and can deal with truly massive datasets, as it is highly scalable and amenable to parallel computations on modern distributed computing systems.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

Copyright © American Statistical Association