Activity Number:
|
80
- Advancement in Spatial and Spatiotemporal Point Process
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, July 29, 2018 : 4:00 PM to 5:50 PM
|
Sponsor:
|
Section on Statistics and the Environment
|
Abstract #328965
|
Presentation
|
Title:
|
Inferring Spatial Point Intensity of Geomagnetic Anomalies from Transect Sampling
|
Author(s):
|
Kenneth Flagg* and Andrew Hoegh and Megan Higgs and John Borkowski
|
Companies:
|
Montana State University and Montana State University and Montana State University and Montana State University
|
Keywords:
|
Bayesian statistics;
spatial point process;
Dirichlet process;
unexploded ordnance
|
Abstract:
|
Geomagnetic anomalies recorded at munitions use sites are often collected along transects that cover a very small proportion of the site area. Munitions items are assumed to occur in elliptical regions of high point intensity, so a primary analysis goal is to map the intensity over the site and identify high-intensity regions that might contain unexploded ordnance. We propose a Bayesian spatial Poisson process model with a Dirichlet process mixture as the inhomogeneous intensity function. Then we incorporate data augmentation into a Gibbs sampler to fit the model to data observed in a subset of the site region. We demonstrate fitting the model to simulated data, using both the fully-observed region and the restriction to two different subsets. Finally, we fit the model to data collected at the Victorville Precision Bombing range in southern California.
|
Authors who are presenting talks have a * after their name.