Techniques for efficient detection of rapid weather changes and analysis of their impacts on a highway network

Abstract

Adverse weather conditions have a significant impact on the safety, mobility, and efficiency of highway networks. Weather contributed to 23 percent of all non-reoccurring delay and approximately 544 million vehicle hours of delay each year (2014). Nearly 2.3 billion dollars each year are spent by transportation agencies for winter maintenance that contribute to close to 20 percent of most DOT’s yearly budgets (2014). These safety and mobility factors make it important to develop new and more effective methods to address road conditions during adverse weather conditions. Given weather and traffic sensors installed along side of the highway networks, how can we automatically detect weather and traffic change events and prevent from the traffic delay or harsh weather accidents? To this end, we propose a novel framework to address this problem. This paper develops techniques for efficiently detecting rapid weather change events and analyzing their impacts on the traffic flow characteristics of a highway network. It is composed of three components, including 1) detection of rapid weather change events in a highway network using the streaming weather information from a sensor network of weather stations; 2) detection of rapid traffic change events on the traffic flow characteristics (e.g., travel time) of the highway network; and 3) analysis of correlations between the detected weather and traffic change events in space and time. The proposed approach was applied to a weather dataset provided by New York State Mesonet and a traffic flow dataset the National Performance Management Research Data Set (NPMRDS) provided by NYSDOT. The empirical results provide potential evidence about the significant impacts of rapid weather change events on traffic flow characteristics of the Interstate 90 (I-90) Highway in the state of New York. We show the quantitative performance evaluation of our change event detection algorithm and three baseline methods on manually labeled the weather dataset and our method outperforms baselines in terms of precision, recall and F-score. We present the analysis of Top K detected change events as case studies and also provide the spatio-temporal correlation statistics of top k weather and traffic change events. The limitations of the proposed approach and the empirical study are also discussed.