A Graph Neural Network Framework for Imbalanced Bus Ridership Forecasting

Public transit systems are paramount in lowering carbon emissions and reducing urban congestion for environmental sustainability. However, overcrowding has adverse effects on the quality of service, passenger experience, and overall efficiency of public transit causing a decline in the usage of public transit systems. Therefore, it is crucial to identify and forecast potential windows of overcrowding to improve passenger experience and encourage higher ridership. Predicting ridership is a complex task, due to the inherent noise of collected data and the sparsity of overcrowding events. Existing studies in predicting public transit ridership consider only a static depiction of bus networks. We address these issues by first applying a data processing pipeline that cleans noisy data and engineers several features for training. Then, we address sparsity by converting the network to a dynamic graph and using a graph convolutional network, incorporating temporal, spatial, and auto-regressive features, to learn generalizable patterns for each route. Finally, since conventional loss functions like categorical cross-entropy have limitations in addressing class imbalance inherent in ridership data, our proposed approach uses focal loss to refine the prediction focus on less frequent yet task-critical overcrowding instances. Our experiments, using real-world data from our partner agency, show that the proposed approach outperforms existing state-of-the-art baselines in terms of accuracy and robustness.

I. Introduction

The transportation sector has a massive environmental impact it contributes 24% of the total carbon dioxide emissions and in the United States, it accounts for 33% of the total greenhouse gas emissions [1], [2]. To address the environmental impact, the US government has increased the budget allocated to the public transportation sector — 42% annual increment from 2022 to 2026 as compared to 2016 to 2021 [3]. Public transportation is at the center of this vision as buses are the cheapest and most accessible form of transit across the country. Travel by bus results in fewer greenhouse gasses per passenger mile in comparison to a typical single-occupancy car [4]. However, public transit is only effective when it becomes a preferred mode of transport over private vehicles.