A Data Model for Determining Weather's Impact on Travel Time

Publikation: Forskning - peer reviewKonferenceartikel i proceeding

Abstrakt

Accurate estimating travel times in road networks is a complex task because travel times depends on factors such as the weather. In this paper, we present a generic model for integrating weather data with GPS data to improve the accuracy of the estimated travel times. First, we present a data model for storing and map-matching GPS data, and integrating this data with detailed weather data. The model is generic in the sense that it can be used anywhere GPS data and weather data is available. Next, we analyze the correlation between travel time and the weather classes dry, fog, rain, and snow along with winds impact on travel time. Using a data set of 1.6 billion GPS records collected from 10,560 vehicles, over a 5 year period from all of Denmark, we show that snow can increase the travel time up to 27% and strong headwind can increase the travel time with up to 19% (compared to dry calm weather). This clearly shows that accurate travel time estimation requires knowledge about the weather.
Luk

Detaljer

Bidragets oversatte titelEn datamodel for bestemmelse af vejrets påvirkning af rejsetider
Accurate estimating travel times in road networks is a complex task because travel times depends on factors such as the weather. In this paper, we present a generic model for integrating weather data with GPS data to improve the accuracy of the estimated travel times. First, we present a data model for storing and map-matching GPS data, and integrating this data with detailed weather data. The model is generic in the sense that it can be used anywhere GPS data and weather data is available. Next, we analyze the correlation between travel time and the weather classes dry, fog, rain, and snow along with winds impact on travel time. Using a data set of 1.6 billion GPS records collected from 10,560 vehicles, over a 5 year period from all of Denmark, we show that snow can increase the travel time up to 27% and strong headwind can increase the travel time with up to 19% (compared to dry calm weather). This clearly shows that accurate travel time estimation requires knowledge about the weather.
OriginalsprogEngelsk
TitelDatabase and Expert Systems Applications : 27th International Conference, DEXA 2016, Porto, Portugal, September 5-8, 2016, Proceedings, Part II
RedaktørerSven Hartman, Hui Ma
Antal sider8
Vol/bind9828
UdgiverSpringer Publishing Company
Publikationsdato8 sep. 2017
Sider437-444
ISBN (trykt)978-3-319-44405-5
ISBN (elektronisk)0302-9743
DOI
StatusUdgivet - 8 sep. 2017
Begivenhed27th International Conference on Database and Expert Systems Applications - DEXA 2016 - Porto, Portugal

Konference

Konference27th International Conference on Database and Expert Systems Applications - DEXA 2016
Lokation GECAD (Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development) at ISEP (Instituto Superior de Engenharia do Porto)
LandPortugal
ByPorto
Periode05/09/201608/09/2016
Internetadresse
SerieLecture Notes in Computer Science
Vol/bind9829
ISSN0302-9743
ID: 249455593