Time-series analysis of severe weather effects on traffic and mobility patterns
Salari, Ehsan Heuer, Adelyn
Salari, Ehsan
Heuer, Adelyn
Authors
Other Names
Location
Time Period
Advisors
Original Date
Digitization Date
Issue Date
2024
Type
Conference paper
Genre
Keywords
Severe weather effects,Traffic and mobility patterns
Subjects (LCSH)
Citation
Heuer, A., & Salari, E. (2024). Time-series analysis of severe weather effects on traffic and mobility patterns. 2024 IISE Annual Conference and Expo. https://iise.confex.com/iise/2024/meetingapp.cgi/Paper/7141
Abstract
Severe weather events can cause significant changes in traffic volume and pattern throughout the day, where certain routes may experience an increased traffic while others may see reduced use. Studying the impact of severe weather events on traffic volume and patterns aids in designing more resilient infrastructure and developing effective emergency response strategies. This research aims at analyzing the existing traffic data to identify disaster-induced mobility and evacuation patterns in the State of Kansas.
We examine the impact of historical severe-weather events in the region, obtained from the National Oceanic and Atmospheric Administration database, on hourly traffic data collected by the U.S. Department of Transportation Federal Highway Administration from 100 stations spread across the State of Kansas. We employ recurrent neural networks to determine if severe-weather events lead to statistical outliers in daily traffic patterns. The long-short-term-memory (LSTM) recurrent neural networks were used to develop a time-series model of hourly traffic flow at different stations. To enhance the goodness of fit, harmonic variables were added to the model to capture daily and weekly seasonality observed in the traffic data. Sensitivity analysis was performed to choose the ideal lag and LSTM network architecture. Outliers were then detected if the hourly forecast as determined by the LSTM network differs with statistical significance from the actual traffic volume. The proposed outlier detection approach was used to analyze the spatial impact of severe weather events on daily traffic patterns in different regions of the state.
Table of Contents
Description
Oral presentation at the 2024 Institute of Industrial & Systems Engineers (IISE) Conference and Expo
Publisher
Institute of Industrial & Systems Engineers (IISE)