Modeling and Transferability of Pedal Cycle Volumes Using Ground Truth,Sensor,Weather,and Crowdsourced Data

Abstract

Understanding active transportation is critical for transportation planning, infrastructure development, and safety improvements. Unlike motor vehicles, which have widespread automated counting stations, cycling and walking automated counting has limited coverage. Given the limited data and unique characteristics of active transportation, it is crucial to evaluate the accuracy of counting technologies and account for temporal variations, weather effects, and transferability when estimating volumes. Data from four sites in Wisconsin were analyzed with 5 years of hourly sensor, weather, and Strava data, along with 268 h of manually processed ground truth video data. Ground truth hourly count trends showed that pedal cycles were the main users in the shared paths (78%–87%). There were peak and directional hourly trends by week or weekend days, higher volumes and a shift in the type of user were observed on weekends. Automatic sensor count data accuracy from inductive loop and infrared sensors was evaluated and compared with ground truth data. Inductive loop counting technology showed high levels of pedal cycle count accuracy (91%–92%). Infrared sensors counted passersby with a reduced degree of accuracy (54%–67%). Negative binomial regression modeling was implemented to account for overdispersion in the count data. Key predictors included time of day, day of the week, month, temperature, precipitation, and Strava counts. Site-specific models were developed, transferability across sites was assessed, and models were generalized with data from sites that shared similar characteristics applicable to high-volume, urban commuting and recreational paths. Models were not transferable to isolated sites with low volume and unreliable sensor count data.