|
Activity Number:
|
251
- Spatial and Spatiotemporal Modeling in Climate and Meteorology
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2018 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
|
Abstract #329021
|
Presentation
|
|
Title:
|
Interval-Valued Kriging and Application in Climate Related Predictions
|
|
Author(s):
|
Brennan Bean* and Yan Sun
|
|
Companies:
|
Utah State University and Utah State University
|
|
Keywords:
|
spatial;
climate;
kriging
|
|
Abstract:
|
Many climate-related measurements are best characterized as intervals rather than single values. Such interval-valued measurements are a result of limitations in sensor technology or other uncertainties in the climate measurement process. While much work has been devoted to the development of interval-valued regression, little has been done to extend the use of interval-valued inputs to traditional spatial methods. This paper proposes and develops interval-valued kriging models based on the theory of random sets and a generalized L2 distance. Numerical implementation of our interval-valued kriging is provided using a penalty-based constrained optimization algorithm. The methodology is then applied to a dataset containing interval-valued snow water equivalent (SWE) measurements in Utah and the results are compared to predictions made using traditional (point-valued) kriging. This application demonstrates the advantages of our interval-valued kriging in climate research, and motivates further developments of interval-valued kriging and other spatial methods
|
Authors who are presenting talks have a * after their name.
