ABSTRACT
This paper examines the case where information on real-time weather conditions is used to predict future speeds in a traveler's route so that they can make travel decisions relating to whether or not to make the trip, change departure time or to take an alternative route, if already on the road. We examine the performance of two different classes of models (a "base" model and a "statistical learning" model) to predict future speeds while controlling for location, demand/time-of-day, prevailing speeds, and future weather conditions. A stratified sampling strategy is adopted with good and bad weather conditions sampled separately within locations along the Eisenhower Expressway in Chicago. We find differences in the predictive abilities of the two models under different weather conditions. The SVM model outperforms the linear regression model by predicting 41% more cases within 3mph of the observed speed under heavy rain conditions, 16.7% more cases within 3mph under snow conditions, 14.5% more cases within 3mph under thunderstorm conditions, and with less dramatic differences under other weather conditions. The results show promise that SVM regression maybe useful in bringing together streaming forecasted weather data and traffic conditions to inform travelers.
- M. Agarwal, T. Maze, and R. Souleyrette. Impacts of weather on urban freeway traffic flow characteristics and facility capacity. In Proceedings of the 2005 Mid-Continent Transportation Research Symposium, Ames, Iowa, 2005.Google Scholar
- R. Billot. Integrating the effects of adverse weather conditions on traffic: Methodology, empirical analysis and bayesian modelling. Young Reseachers Seminar, 2009.Google Scholar
- B. Brown and K. Baass. Seasonal variation in frequencies and rates of highway accidents as function of severity. Transportation Research Record: Journal of the Transportation Research Board, 1581(-1):59--65, 1997.Google ScholarCross Ref
- R. Cheu, J. Xu, A. Kek, W. Lim, and W. Chen. Forecasting shared-use vehicle trips with neural networks and support vector machines. Transportation Research Record: Journal of the Transportation Research Board, 1968(-1):40--46, 2006.Google Scholar
- S. Chin, O. Franzese, D. Greene, H. Hwang, and R. Gibson. Temporary Losses of Highway Capacity and Impacts on Performance: Phase 2. United States. Dept. of Energy, 2004.Google ScholarCross Ref
- E. Chung, O. Ohtani, H. Warita, M. Kuwahara, and H. Morita. Does weather affect highway capacity. 2006.Google Scholar
- D. Dailey and T. Trepanier. The Use of Weather Data to Predict Non-recurring Traffic Congestion. Technical report, Technical report to Washington State Transportation Commission, Washington State Department of Transportation, University of Washington TransNow, and Federal Highway Administration, 2006.Google Scholar
- E. Dimitriadou, K. Hornik, F. Leisch, D. Meyer, and A. Weingessel. e1071: Misc Functions of the Department of Statistics (e1071), TU Wien, 2009. R package version 1.5--22.Google Scholar
- S. Drobot, W. Mahoney III, E. Schuler, G. Wiener, M. Chapman, P. Pisano, P. Kennedy, B. McKeever, A. Stern, and I. Noblis. IntelliDrive road weather research & development-the vehicle data translator. Proceedings of the 2009 Intelligent Transportation Systems World Congress, 2009.Google Scholar
- J. Edwards. The relationship between road accident severity and recorded weather. Journal of Safety Research, 29(4):249--262, 1998.Google ScholarCross Ref
- D. Eisenberg. The mixed effects of precipitation on traffic crashes. Accident Analysis & Prevention, 36(4):637--647, 2004.Google Scholar
- L. Goodwin. Weather impacts on arterial traffic flow. Mitretek Systems Inc., Jan 2002.Google Scholar
- R. Hanbali and D. Kuemmel. Traffic volume reductions due to winter storm conditionõs. Transportation Research Board, 1387:159--164, 1993.Google Scholar
- R. Hranac, E. Sterzin, D. Krechmer, H. Rakha, and M. Farzaneh. Empirical studies on traffic flow in inclement weather. Technical report, 2006.Google Scholar
- S. Huang and B. Ran. An application of neural network on traffic speed prediction under adverse weather condition. In 82nd TRB Annual Meeting (CD-ROM), 2003.Google Scholar
- A. Ibrahim and F. Hall. Effect of adverse weather conditions on speed-flow-occupancy relationships. Transportation Research Board, Jan 1994.Google Scholar
- K. Keay and I. Simmonds. The association of rainfall and other weather variables with road traffic volume in Melbourne, Australia. Accident Analysis & Prevention, 37(1):109--124, 2005.Google Scholar
- A. Khattak, P. Kantor, and F. Council. Role of Adverse Weather in Key Crash Types on Limited-Access: Roadways Implications for Advanced Weather Systems. Transportation Research Record: Journal of the Transportation Research Board, 1621(-1):10--19, 1998.Google Scholar
- K. Knapp, L. Smithson, and A. Khattak. The mobility and safety impacts of winter storm events in a freeway environment. Mid-Continent Transportation Symposium Proceedings, 2000.Google Scholar
- M. Kyte, Z. Khatib, P. Shannon, and F. Kitchener. Effect of weather on free-flow speed. Transportation Research Record: Journal of the Transportation Research Board, 1776(-1):60--68, 2001.Google ScholarCross Ref
- La Montre Verde. Greenwatch/city pulse. http://www.lamontreverte.org/en/, 2009. Accessed on July 31, 2010.Google Scholar
- H. Mahmassani, J. Dong, J. Kim, R. Chen, and B. Park. Incorporating Weather Impacts in Traffic Estimation and Prediction Systems. Technical report, 2009.Google Scholar
- T. Maze, M. Agarwai, and G. Burchett. Whether weather matters to traffic demand, traffic safety, and traffic operations and flow. Transportation Research Record: Journal of the Transportation Research Board, 1948(-1):170--176, 2006.Google Scholar
- K. Meead Saberi and R. Bertini. Empirical analysis of the effects of rain on measured freeway traffic parameters. In 89th Annual Meeting of the Transportation Research Board, 2010.Google Scholar
- E. Moons, G. Wets, and M. Aerts. Nonlinear models for determining mode choice. Progress in Artificial Intelligence, pages 183--194, 2007. Google ScholarDigital Library
- National Weather Service. Storm reports via a twitter. http://www.weather.gov/stormreports/, 2009. Accessed on July 31, 2010.Google Scholar
- L. Nookala. Weather Impact on Traffic Conditions and Travel Time Prediction. Master's thesis, University of Minnesota, 2006.Google Scholar
- Z. Peng, F. Wu, and Z. Jiang. Prediction of railway passenger traffic volume by means of ls-svm. Advances in Neural Networks-ISNN 2006, pages 8--14, 2006. Google ScholarDigital Library
- X. Qi-hua and Y. Rui. Traffic Flow Prediction Using Support Vector Machine Based Method {J}. Journal of Highway and Transportation Research and Development, 12, 2005.Google Scholar
- R Development Core Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria, 2009. ISBN 3-900051-07-0.Google Scholar
- M. Sabir, J. V. Ommeren, M. Koetse, and P. Rietveld. Adverse weather and commuting speed. Networks and Spatial Economics, pages 1--12, 2010.Google Scholar
- V. Shankar, F. Mannering, and W. Barfield. Effect of roadway geometrics and environmental factors on rural freeway accident frequencies. Accident Analysis & Prevention, 27(3):371--389, 1995.Google Scholar
- B. Smith, K. Byrne, R. Copperman, S. Hennessy, and N. Goodall. An investigation into the impact of rainfall on freeway traffic flow. In 83rd annual meeting of the Transportation Research Board, Washington DC, 2004.Google Scholar
- J. L. P. M. R. S. W. P. Thakuriah, P. G. Yanos and L. Mbekeani. Including weather effects in real-time traffic information environment - exploratory analysis and alternative models. In Proceedings of the 15th Intelligent Transportation Systems World Congress, New York City, 2008.Google Scholar
- H. Tu, J. Van Lint, and H. Van Zuylen. The impact of adverse weather on travel time variability of freeway corridors. In 86th Annual Meeting of the Transportation Research Board Papers CD-ROM, 2007.Google Scholar
- Y. Zhang and Y. Xie. Travel mode choice modeling with support vector machines. Transportation Research Record: Journal of the Transportation Research Board, 2076(-1):141--150, 2008.Google Scholar
Index Terms
- Using real-time weather information for traveler information: a statistical learning application under alternative experimental conditions
Recommendations
Weather Prediction Model using Savitzky-Golay and Kalman Filters
AbstractDaily Weather forecasting is essential in multiple areas like agriculture, energy supply, transportation and so on. It is a predictive challenge that has mainly relied on model based methods. We explore new techniques for forecasting weather with ...
Time series forecasting by a seasonal support vector regression model
The support vector regression (SVR) model is a novel forecasting approach and has been successfully used to solve time series problems. However, the applications of SVR models in a seasonal time series forecasting has not been widely investigated. This ...
Weather analysis using ensemble of connectionist learning paradigms
This paper presents a comparative analysis of different connectionist and statistical models for forecasting the weather of Vancouver, Canada. For developing the models, one year's data comprising of daily temperature and wind speed were used. A multi-...
Comments