Non-Stationary Time Series Model for Station-Based Subway Ridership During COVID-19 Pandemic: Case Study of New York City

The COVID-19 pandemic in 2020 has caused sudden shocks in transportation systems, specifically the subway ridership patterns in New York City (NYC), U.S. Understanding the temporal pattern of subway ridership through statistical models is crucial during such shocks. However, many existing statistical frameworks may not be a good fit to analyze the ridership data sets during the pandemic, since some of the modeling assumptions might be violated during this time. In this paper, utilizing change point detection procedures, a piecewise stationary time series model is proposed to capture the nonstationary structure of subway ridership. Specifically, the model consists of several independent station based autoregressive integrated moving average (ARIMA) models concatenated together at certain time points. Further, data-driven algorithms are utilized to detect the changes of ridership patterns as well as to estimate the model parameters before and during the COVID-19 pandemic. The data sets of focus are daily ridership of subway stations in NYC for randomly selected stations. Fitting the proposed model to these data sets enhances understanding of ridership changes during external shocks, both in relation to mean (average) changes and the temporal correlations.

Non-Stationary Time Series Model for Station-Based Subway Ridership During COVID-19 Pandemic: Case Study of New York City.

The COVID-19 pandemic in 2020 has caused sudden shocks in transportation systems, specifically the subway ridership patterns in New York City (NYC), U.S. Understanding the temporal pattern of subway ridership through statistical models is crucial during such shocks. However, many existing statistical frameworks may not be a good fit to analyze the ridership data sets during the pandemic, since some of the modeling assumptions might be violated during this time. In this paper, utilizing change point detection procedures, a piecewise stationary time series model is proposed to capture the nonstationary structure of subway ridership. Specifically, the model consists of several independent station based autoregressive integrated moving average (ARIMA) models concatenated together at certain time points. Further, data-driven algorithms are utilized to detect the changes of ridership patterns as well as to estimate the model parameters before and during the COVID-19 pandemic. The data sets of focus are daily ridership of subway stations in NYC for randomly selected stations. Fitting the proposed model to these data sets enhances understanding of ridership changes during external shocks, both in relation to mean (average) changes and the temporal correlations.

Non-Stationary Time Series Model for Station Based Subway Ridership During Covid-19 Pandemic (Case Study: New York City)

The COVID-19 pandemic in 2020 has caused sudden shocks in transportation systems, specifically the subway ridership patterns in New York City. Understanding the temporal pattern of subway ridership through statistical models is crucial during such shocks. However, many existing statistical frameworks may not be a good fit to analyze the ridership data sets during the pandemic since some of the modeling assumption might be violated during this time. In this paper, utilizing change point detection procedures, the authors propose a piece-wise stationary time series models to capture the nonstationary structure of subway ridership. Specifically, the model consists of several independent station based autoregressive integrated moving average (ARIMA) models concatenated together at certain time points. Further, data-driven algorithms are utilized to detect the changes of ridership patterns as well as to estimate the model parameters before and after the COVID-19 pandemic. The data sets of focus are daily ridership of subway stations in New York City for randomly selected stations. Fitting the proposed model to these data sets enhances our understanding of ridership changes during external shocks, both in terms of mean (average) changes as well as the temporal correlations.

An estimation of the effects of social distancing measures on transit vehicle capacity and operations.

The COVID-19 pandemic has a direct impact on public transport operations. In this paper, impacts on transit operations of the physical distancing measures deployed to slow the spread of the virus are analyzed and recommendations are provided. At first, two social distancing optimization solutions are provided in order to keep riders at a safe distance. The first is a discrete optimization that can be used in buses with fixed seats, while the second is a continuous optimization that can be used to distribute riders on a grid and be applied on a bus or subway platform. Assuming that the ridership will eventually go back to its level before the pandemic, the second objective of this research is to address the transit operation parameters that need to be changed in order to serve the pre-COVID ridership level, while respecting the social distancing measures. An O-D distribution has been developed in this paper for New York City (NYC) subway line 1, based on the 2018 NYC Travel Survey conducted by the Metropolitan Transportation Authority. Five scenarios of physical distancing are simulated and analyzed in this paper: 3ft, 4ft, 5ft, 5.4ft, and 6ft of separation between passengers. The results show the number of additional trains required to accommodate the hypothetical pre-COVID ridership demand while maintaining social distancing. An interesting key finding is that, by decreasing the minimum distance from 6ft to 5.4ft, the number of additional trains required to serve the transit demand drastically decreases and hence more resources are saved.