Online Program Home
  My Program

Abstract Details

Activity Number: 521 - Contributed Poster Presentations: Quality and Productivity Section
Type: Contributed
Date/Time: Wednesday, August 2, 2017 : 10:30 AM to 12:20 PM
Sponsor: Quality and Productivity Section
Abstract #322586
Title: Space-Time Outlier Identification in a Large Ground Deformation Dataset
Author(s): Youjiao Yu* and Austin Workman and Amanda S. Hering
Companies: Department Statistical Science, Baylor University and Baylor University and Baylor University
Keywords: Big Data ; Outlier Detection ; Spatial-Temporal ; Robust Kriging
Abstract:

A novel but important application for outlier detection methodologies is in ground deformation monitoring. During any type of underground construction in urban settings, sensors are placed on the ground surface to monitor the surface height with the goal of ensuring that there is no substantial heaving or settling of the ground. As a result, a large spatial-temporal dataset is produced, but the sensors are often very sensitive, and spurious readings are commonly observed. In this work, we present a novel, fast spatial-temporal monitoring procedure that is designed to remove these spurious readings prior to subsequent ground deformation monitoring. First, a robust regression is applied to the time series of ground deformations at each spatial location to remove temporal outliers; and next, robust kriging is applied to the ground deformations observed in space to remove spatial outliers. A case study using ground deformation data when four subway tunnels are bored under a rail yard in Queens, New York is used to illustrate the methodology.


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

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association