Citation

Shah NR, Guo J, Han LD, Cherry CR. Transp. Res. A Policy Pract. 2023; 173: e103705.

Copyright

(Copyright © 2023, Elsevier Publishing)

DOI

10.1016/j.tra.2023.103705

PMID

unavailable

Abstract

Electric scooters (e-scooters) are becoming one of the most popular micromobility options in the United States. Although there is some evidence of increased mobility, reduced carbon emissions, replaced car trips, and associated public health benefits, there is little known about the patterns of e-scooter use. This study proposes a framework for high-resolution analysis of micromobility data based on temporal, spatial, and weather attributes. As a case study, we scrutinized more than one million e-scooter trips of Nashville, Tennessee, from September 1, 2018, to August 31, 2019. Weather data and land use data from the Nashville Travel Demand Model and scraping of Google Maps Point of Interest (POI) data complemented the trip data. The combination of Principal Component Analysis (PCA) and a K-means unsupervised machine learning algorithm identified five distinct e-scooter usage patterns, namely morning work/school, daytime short errand, social, nighttime entertainment district, and utilitarian trips. Among other findings, the most common use of e-scooters in Nashville was daytime short errand trips, contributing to 29% of all e-scooter trips. We found that 7% of all e-scooter trips resembled morning commuting to work or school. Only 16% of trips were classified as Nighttime Entertainment District trips. The average daily number of trips on a typical weekend was 81% higher than a typical weekday. We also found variation in e-scooter usage patterns over a year with high summer ridership patterns. The findings of this study can help city administrations, planners, and micromobility operators to understand when and where people are using e-scooters. Such knowledge can guide them in making data-driven decisions regarding safety, sustainability, and mode substitution of emerging micromobility.

Language: en

Keywords

Big data; E-scooters; Micromobility; Spatiotemporal analysis; Unsupervised machine learning