01519058

Component

Weather conditions have considerable impact on freeway free-flow characteristics. Several empirical studies have stated that precipitation, snow, and visibility loss may cause reductions in speed and capacity. Therefore, identifying promising predictors among these meteorological factors is a crucial issue for traffic flow prediction. However, the complex features (irregularities, volatility, trends and noise) inherent in temporally aggregated observed data make it a rather difficult problem. Moreover, in contrast to the development of predictive models to determine the precise numerical information of traffic parameters, it may be more meaningful to predict the free-flow trend on major freeways with reasonable accuracy. Besides, in the particular case of time series forecasting, another crucial element necessary to determine is lagged effects of weather conditions on free-flow. Therefore, a detailed investigation in this paper was carried out to examine the linkages between meteorological factors and key traffic stream parameters. The study was based on recent archived data from sensor devices, such as inductive loop detectors and weather sensors, located on provincial freeways of Jilin Province in China. The trend and cyclical components were firstly separated from weather and free-flow parameter series by using filtering technique. Then a multiple-equation system known as a vector autoregression (VAR) was proposed for characterizing the temporal dynamics inherent in these components, while Granger causality theory was adopted to identify the existence of a systemic causal relationship for attribute selection. Furthermore, the recently developed method of impulse response function provided insight into the lagged effects of these traffic parameters and their responses to weather conditions, and the multiple series data are reconstructed by incorporating the lagged periods. Finally, various classification models are compared in terms of trend prediction accuracy, Receiver Operating Characteristic (ROC) curve. As a result, K-NN model outperforms the others for the overall predication performance, while results also indicate a significant performance improvement for these models by incorporating the lagged effects. Besides, some interesting results were also concluded from this study, including descriptions of the dynamic interplay among variables, as well as the possible variations in hourly freeway traffic activities with respect to weather trends. It is hoped that this study will shed light on a full understanding of how weather factors affect freeway traffic conditions.

This paper was sponsored by TRB committee AH010 Surface Transportation Weather. Alternate title: Analysis of Weather-Lagged Effects on Freeway Free-Flow Characteristics in Jilin, China.

01503729

14-5156

English

17p

2014

Transportation Research Board 93rd Annual Meeting

Digital/other

Figures; References; Tables

Free flow speeds; Freeways; Highway capacity; Time series analysis; Traffic flow; Weather conditions

Lag time

Jilin Province (China)

Highways; Planning and Forecasting; I72: Traffic and Transport Planning

Transportation Research Board Annual Meeting 2014 Paper #14-5156

TRIS, TRB, ATRI

Jan 27 2014 3:48PM