A Hybrid Geostatistical Method for Estimating Citywide Traffic Volumes – A Case Study of Edmonton, Canada

Traffic volume information has long played an important role in many transportation related works, such as traffic operations, roadway design, air quality control, and policy making. However, monitoring volumes over a large spatial area is not easy task due to the significant amount of time manpower required collect large-scale datasets. In this study, hybrid geostatistical approach, named Network Regression Kriging,has been developed estimate urban by incorporating auxiliary variables road type, speed limit, network accessibility.Since standard kriging based on Euclidean distances, study implements distances improve estimations.A case using 10-year data collected within city Edmonton was conducted demonstrate robustness model herein. Results suggest that proposed significantly outperforms method terms accuracy 4.0% overall, especially for network. It also found necessary stationarity assumption did hold true whereby separate estimations each type performed better than general estimation overall 4.12%.