Abstract
Abstract. Since early 2020, the number of COVID-19 cases has continued its rise and fall worldwide, greatly impacting sectors such as health outcomes, economics, housing, and transportation. To mitigate the spread of the pandemic, governments implemented various measures to reduce the mobility of the population, restricting international travel, hierarchical lockdowns, stay-at-home mandates, and work-from-home orders. In this aspect, early studies in the transportation field showed large changes in travel behaviour. However, we know less about the long-term impact of COVID-19 on people's travel behaviour. This paper explores the change in commute behaviour during the pandemic, focusing on the resilience index of transit users and its determining factors. The hist gradient boosting model was the most precise when compared with linear and other machine learning models (considering R2, MSE, MAE). The results suggested the following: (1) commuters' trips decreased unevenly in Seoul. Through machine learning algorithms, social-economic factors, and accessibility, 50% of the heterogeneity can be explained. (2) Consumer and Service Industry and Foreigner Tourism were impacted negatively continually. Neighbourhoods with higher car ownership and a higher percentage of female residents show long term weak public transit resilience. (2) Short distance commuters (less than 20 minutes) and commuters visiting city centres, returned to public transport in the second year after avoiding it during the first year of the pandemic. Considering the uneven negative results of COVID-19, this research can be a reference for policy design and effective decision making.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.