Predicting Public Transportation Load to Estimate the Probability of Social Distancing Violations

Juan Martinez, Ayan Mukhopadhyay Afiya Ayman, Michael Wilbur, Philip Pugliese, Dan Freudberg, Aron Laszka, Abhishek Dubey

Proceedings of the Workshop on AI for Urban Mobility at the 35th AAAI Conference on Artificial Intelligence (AAAI-21) 2021

PDF

Why This Matters

During the COVID-19 pandemic, transit agencies faced unprecedented challenges in maintaining public health while preserving service accessibility. Accurate prediction of ridership demand is essential for optimizing transit schedules and ensuring that social distancing protocols can be maintained on buses. This work is innovative because it bridges data-driven ridership forecasting with public health constraints, providing transit planners with evidence-based tools to make operational decisions that protect both passengers and drivers.

What We Did

This paper develops statistical models to predict public transit ridership patterns and estimate the probability of social distancing violations during the COVID-19 pandemic. The researchers use automated passenger counting data and General Transit Feed Specification information from two major metropolitan areas to build predictive models including Poisson, negative binomial, zero-inflated Poisson, and zero-inflated negative binomial distributions. These models capture board and alight counts across different bus stops and times of day, accounting for temporal heterogeneity in transit demand.

Key Results

The zero-inflated statistical models demonstrated superior performance in predicting both board and alight counts compared to standard Poisson models, with particularly good performance on test data from June 2020. The models enable transit agencies to estimate hourly ridership patterns and identify peak demand periods, allowing for dynamic capacity adjustments and social distancing compliance. Results show that the approach can provide actionable insights for transit operators planning safe operations during pandemic and post-pandemic periods.

Full Abstract

Cite This Paper

@inproceedings{juan21,
  author = {Martinez, Juan and Ayman, Ayan Mukhopadhyay Afiya and Wilbur, Michael and Pugliese, Philip and Freudberg, Dan and Laszka, Aron and Dubey, Abhishek},
  booktitle = {Proceedings of the Workshop on AI for Urban Mobility at the 35th AAAI Conference on Artificial Intelligence (AAAI-21)},
  title = {Predicting Public Transportation Load to Estimate the Probability of Social Distancing Violations},
  year = {2021},
  abstract = {Public transit agencies struggle to maintain transit accessibility with reduced resources, unreliable ridership data, reduced vehicle capacities due to social distancing, and reduced services due to driver unavailability. In collaboration with transit agencies from two large metropolitan areas in the USA, we are designing novel approaches for addressing the afore-mentioned challenges by collecting accurate real-time ridership data, providing guidance to commuters, and performing operational optimization for public transit. We estimate rider-ship data using historical automated passenger counting data, conditional on a set of relevant determinants. Accurate ridership forecasting is essential to optimize the public transit schedule,  which is necessary to improve current fixed lines with on-demand transit. Also, passenger crowding has been a problem for public transportation since it deteriorates passengers' wellbeing and satisfaction. During the COVID-19 pandemic, passenger crowding has gained importance since it represents a  risk for social distancing violations. Therefore, we are creating optimization models to ensure that social distancing norms can be adequately followed while ensuring that the total demand for transit is met. We will then use accurate forecasts for operational optimization that includes \textit{(a)} proactive fixed-line schedule optimization based on predicted demand, \textit{(b)} dispatch of on-demand micro-transit, prioritizing at-risk populations, and \textit{(c)} allocation of vehicles to transit and cargo trips, considering exigent vehicle maintenance requirements (\textit{i.e.}, disinfection). Finally, this paper presents some initial results from our project regarding the estimation of ridership in public transit.},
  contribution = {minor},
  tag = {transit},
  keywords = {transit ridership prediction, COVID-19, social distancing, public transportation, statistical modeling, automated passenger counting, zero-inflated models}
}
Quick Info
Year 2021
Keywords
transit ridership prediction COVID-19 social distancing public transportation statistical modeling automated passenger counting zero-inflated models
Research Areas
transit planning ML for CPS
Search Tags

Predicting, Public, Transportation, Load, Estimate, Probability, Social, Distancing, Violations, transit ridership prediction, COVID-19, social distancing, public transportation, statistical modeling, automated passenger counting, zero-inflated models, transit, planning, ML for CPS, 2021, Martinez, Ayman, Wilbur, Pugliese, Freudberg, Laszka, Dubey