Evaluating Mobility Impacts of Construction Work Zones on Utah Transportation System Using Machine Learning Techniques
Author/Presenter: Mashhadi, Ali Hassandokht; Rashidi, AbbasAbstract:
Construction work zones are inevitable parts of daily operations at roadway systems. They have a significant impact on traffic conditions and the mobility of roadway systems. The traffic impacts of work zones could significantly vary due to several interacting factors such as work zone factors (work zone location and layout, length of the closure, work zone speed, intensity, and daily active hours); traffic factors (percentage of heavy vehicles, highway speed limit, capacity, mobility, flow, density, congestion, and occupancy); road factors (number of total lanes, number of open lanes, and pavement grade and condition); temporal factors (e.g., year, season, month, weekday, daytime, and darkness); weather conditions (rainy, sunny, and snowy); and spatial factors (road lane width, proximity, and number of ramps).
Utah Department of Transportation (UDOT) is continuously collecting and storing project-related data. Due to the significant impact of work zones on traffic conditions, they are interested in evaluating the impacts of work zone attributes on mobility and traffic conditions of roadway systems within the state of Utah. Such an analysis will help the UDOT personnel better understand and plan for more efficient work zone operations, select the most effective traffic management systems for work zones, and assess the hidden costs of construction operations at work zones.
To help UDOT address this problem, we propose a robust, deep neural network (DNN) model capable of evaluating the impacts of the factors mentioned earlier on the mobility conditions of Utah roadway systems. DNNs can capture all the relationships between input variables and output compared to traditional machine learning algorithms. The results of this project show that work zone features have an important effect on the traffic condition. In the end, the performance of the model is evaluated using three different measures, including R2 score, RMSE, and MAE. Comparing the measurement to previously conducted research, it is the first study that has attempted to investigate the effect of work zone features on hourly traffic volume.
Publication Date: September 2021
Full Text URL: Link to URL
Publication Types: Books, Reports, Papers, and Research Articles
Topics: Impacts; Machine Learning; Traffic Estimation; Work Zone Capacity; Work Zones