In Light of the Automated Fare Collection Data, How Did the Travel Patterns of Transit Riders in Tehran Change following COVID-۱۹?

The spread of COVID-۱۹ caused some problems in public transportation. The pandemic created new challenges for developing countries like Iran, where public transportation is already plagued by many problems. As a result of COVID-۱۹ concerns, it was speculated that unpredictable travel patterns would result. Based on Automatic Fare Collection data, in which passengers use a smartcard to enter a stop, this study evaluates this speculation. The dataset includes one month of transactions for each of the three COVID-۱۹-related years (۲۰۱۹, ۲۰۲۰, and ۲۰۲۱) in Tehran, the country's capital. By using time series clustering, it was found that a new pattern of travel has emerged. Before vaccination, most origins were in the eastern part of the city; whereas, in the new era, most of the origins are in the western part of the city. The peak hours have also undergone a significant change. Prior to the pandemic, the peak hour occurred between ۷ and ۸ o'clock in the morning, and demand reduced until the evening peak hour, but as a result of the new pattern, demand did not decrease significantly after ۸:۰۰:۰۰, which resulted in new peak hours. It is anticipated that these changes will have a domino effect on Tehran's transit system as a whole. The system may not be able to handle the changes in behavior, as it was designed to deal with pre-pandemic behavior patterns. There is a need for rescheduling to resolve the problem. Additionally, the government should develop a long-term plan for restoring public transportation demand to its pre-pandemic level.

کلیدواژه ها:

public transportation ، COVID-۱۹ vaccination ، Transit Ridership ، Machine Learning ، Time series Clustering