Best Practices for Road Weather Management Version 2.0
Title:
The Analysis of Winter Maintenance Logs using Regression Tree Algorithm
Abstract:
Recently, many state agencies in the U.S. have made rigorous efforts to log and archive their winter maintenance activities. This study analyzed major contributing variables to "speed recovery duration," which is the time interval from when a winter weather event starts to when the roadway becomes wet condition using a regression tree algorithm "GUIDE" (Generalized, Unbiased, Interaction, Detection and Estimation). A total of 12,526 snow storm reports in Wisconsin since 1998 were analyzed. To represent the performance of winter maintenance, a variable, "PassRatio," was developed. It is defined as the time interval between when a "winter weather event starts" and when the "roadway becomes passable" over the duration of the winter weather event. According to the analysis with regression tree algorithm, GUIDE, it seems that "CrewDelayed" is a significant independent variable that has a significant association with "PassRatio."
Source(s):
85th Transportation Research Board (TRB) Annual Meeting, University of Wisconsin-Madison. For an electronic copy of this resource, please direct your request to WeatherFeedback@dot.gov.
Date: 2006
Author:
Lee, Ran, Qin
Keywords:
Pavement condition
Winter storm
Snow
PDF files can be viewed with the Acrobat® Reader®.