Online Program Home
My Program

Abstract Details

Activity Number: 90 - Invited EPoster Session
Type: Invited
Date/Time: Sunday, July 28, 2019 : 8:30 PM to 10:30 PM
Sponsor: ASA
Abstract #307431
Title: A Case Study Comparison of Predictive Accuracy and Uncertainty Quantification Among Methods for Analyzing Large Spatial Data
Author(s): Matthew Heaton*
Companies: Brigham Young University
Keywords: Big data; Gaussian process; Parallel computing; Low rank approximation
Abstract:

The Gaussian process is an indispensable tool for spatial data analysts. The onset of the "big data" era, however, has lead to the traditional Gaussian process being computationally infeasible for modern spatial data. As such, various alternatives to the full Gaussian process that are more amenable to handling big spatial data have been proposed. These modern methods often exploit low rank structures and/or multi-core and multi-threaded computing environments to facilitate computation. This study describes the results of a predictive competition among the various methods as implemented by different groups with strong expertise in the methodology. Specifically, each research group was provided with two training datasets (one simulated and one observed) along with a set of prediction locations. Each group then wrote their own implementation of their method to produce predictions (along with prediction uncertainties) at the given location and each was subsequently run on a common computing environment. The methods were then compared in terms of various predictive diagnostics.


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

Back to the full JSM 2019 program