Search

Urban prediction tasks, such as forecasting traffic flow, temperature, and crime rates, are crucial for efficient urban planning and management. However, existing Spatiotemporal Graph Neural Networks (ST-GNNs) often rely solely on accuracy, overlooking spatial and demographic disparities in their predictions. This oversight can lead to imbalanced resource allocation and exacerbate existing inequities in urban areas. This study introduces a Residual-Aware Attention (RAA) Block and an equality-enhancing loss function to address these disparities. By adapting the adjacency matrix during training and incorporating spatial disparity metrics, our approach aims to reduce local segregation of residuals and errors. We applied our methodology to urban prediction tasks in Chicago, utilizing a travel demand dataset as an example. Our model achieved a 48% significant improvement in fairness metrics with only a 9% increase in error metrics. Spatial analysis of residual distributions revealed that models with RAA Blocks produced more equitable prediction results, particularly by reducing errors clustered in central regions. Attention maps demonstrated the model's ability to dynamically adjust focus, leading to more balanced predictions. Case studies of various community areas in Chicago further illustrated the effectiveness of our approach in addressing spatial and demographic disparities, supporting more balanced and equitable urban planning and policy-making.

Effective traffic prediction is a cornerstone of intelligent transportation systems, enabling precise forecasts of traffic flow, speed, and congestion. While traditional spatio-temporal graph neural networks (ST-GNNs) have achieved notable success in short-term traffic forecasting, their performance in long-term predictions remains limited. This challenge arises from over-squashing problem, where bottlenecks and limited receptive fields restrict information flow and hinder the modeling of global dependencies. To address these challenges, this study introduces a novel framework that incorporates virtual nodes, which are additional nodes added to the graph and connected to existing nodes, in order to aggregate information across the entire graph within a single GNN layer. Our proposed model incorporates virtual nodes by constructing a semi-adaptive adjacency matrix. This matrix integrates distance-based and adaptive adjacency matrices, allowing the model to leverage geographical information while also learning task-specific features from data. Experimental results demonstrate that the inclusion of virtual nodes significantly enhances long-term prediction accuracy while also improving layer-wise sensitivity to mitigate the over-squashing problem. Virtual nodes also offer enhanced explainability by focusing on key intersections and high-traffic areas, as shown by the visualization of their adjacency matrix weights on road network heat maps. Our advanced approach enhances the understanding and management of urban traffic systems, making it particularly well-suited for real-world applications.

Surveys and interviews (structured, semi-structured, or unstructured) are widely used for collecting insights on emerging or hypothetical scenarios. Traditional human-led methods often face challenges related to cost, scalability, and consistency. Recently, various domains have begun to explore the use of conversational agents (chatbots) powered by large language models (LLMs). However, as public investments and policies on infrastructure and services often involve substantial public stakes and environmental risks, there is a need for a rigorous, transparent, privacy-preserving, and cost-efficient development framework tailored for such major decision-making processes. This paper addresses this gap by introducing a modular approach and its resultant parameterized process for designing conversational agents. We detail the system architecture, integrating engineered prompts, specialized knowledge bases, and customizable, goal-oriented conversational logic in the proposed approach. We demonstrate the adaptability, generalizability, and efficacy of our modular approach through three empirical studies: (1) travel preference surveys, highlighting multimodal (voice, text, and image generation) capabilities; (2) public opinion elicitation on a newly constructed, novel infrastructure project, showcasing question customization and multilingual (English and French) capabilities; and (3) transportation expert consultation about future transportation systems, highlighting real-time, clarification request capabilities for open-ended questions, resilience in handling erratic inputs, and efficient transcript post-processing. The results show the effectiveness of this modular approach and how it addresses key ethical, privacy, security, and token consumption concerns, setting the stage for the next-generation surveys and interviews.

Vision language models (VLMs) have demonstrated impressive performance across a wide range of downstream tasks. However, their proficiency in spatial reasoning remains limited, despite its crucial role in tasks involving navigation and interaction with physical environments. Specifically, most of these tasks rely on the core spatial reasoning capabilities in two-dimensional (2D) environments, and our evaluation reveals that state-of-the-art VLMs frequently generate implausible and incorrect responses to composite spatial reasoning problems, including simple pathfinding tasks that humans can solve effortlessly at a glance. To address this, we explore an effective approach to enhance 2D spatial reasoning within VLMs by training the model solely on basic spatial capabilities. We begin by disentangling the key components of 2D spatial reasoning: direction comprehension, distance estimation, and localization. Our central hypothesis is that mastering these basic spatial capabilities can significantly enhance a model's performance on composite spatial tasks requiring advanced spatial understanding and combinatorial problem-solving, with generalized improvements in visual-spatial tasks. To investigate this hypothesis, we introduce Sparkle, a framework that fine-tunes VLMs on these three basic spatial capabilities by synthetic data generation and targeted supervision to form an instruction dataset for each capability. Our experiments demonstrate that VLMs fine-tuned with Sparkle achieve significant performance gains, not only in the basic tasks themselves but also in generalizing to composite and out-of-distribution spatial reasoning tasks. These findings underscore the effectiveness of mastering basic spatial capabilities in enhancing composite spatial problem-solving, offering insights into systematic strategies for improving VLMs' spatial reasoning capabilities.

Graph Neural Networks deliver strong classification results but often suffer from poor calibration performance, leading to overconfidence or underconfidence. This is particularly problematic in high stakes applications where accurate uncertainty estimates are essential. Existing post hoc methods, such as temperature scaling, fail to effectively utilize graph structures, while current GNN calibration methods often overlook the potential of leveraging diverse input information and model ensembles jointly. In the paper, we propose Graph Ensemble Temperature Scaling, a novel calibration framework that combines input and model ensemble strategies within a Graph Mixture of Experts archi SOTA calibration techniques, reducing expected calibration error by 25 percent across 10 GNN benchmark datasets. Additionally, GETS is computationally efficient, scalable, and capable of selecting effective input combinations for improved calibration performance.

Quantifying uncertainty is crucial for robust and reliable predictions. However, existing spatiotemporal deep learning mostly focuses on deterministic prediction, overlooking the inherent uncertainty in such prediction. Particularly, highly-granular spatiotemporal datasets are often sparse, posing extra challenges in prediction and uncertainty quantification. To address these issues, this paper introduces a novel post-hoc Sparsity-awar Uncertainty Calibration (SAUC) framework, which calibrates uncertainty in both zero and non-zero values. To develop SAUC, we firstly modify the state-of-the-art deterministic spatiotemporal Graph Neural Networks (ST-GNNs) to probabilistic ones in the pre-calibration phase. Then we calibrate the probabilistic ST-GNNs for zero and non-zero values using quantile approaches.Through extensive experiments, we demonstrate that SAUC can effectively fit the variance of sparse data and generalize across two real-world spatiotemporal datasets at various granularities. Specifically, our empirical experiments show a 20\% reduction in calibration errors in zero entries on the sparse traffic accident and urban crime prediction. Overall, this work demonstrates the theoretical and empirical values of the SAUC framework, thus bridging a significant gap between uncertainty quantification and spatiotemporal prediction., Comment: Paper accepted by ACM SIGSPATIAL 2024

This study addresses the problem of convolutional kernel learning in univariate, multivariate, and multidimensional time series data, which is crucial for interpreting temporal patterns in time series and supporting downstream machine learning tasks. First, we propose formulating convolutional kernel learning for univariate time series as a sparse regression problem with a non-negative constraint, leveraging the properties of circular convolution and circulant matrices. Second, to generalize this approach to multivariate and multidimensional time series data, we use tensor computations, reformulating the convolutional kernel learning problem in the form of tensors. This is further converted into a standard sparse regression problem through vectorization and tensor unfolding operations. In the proposed methodology, the optimization problem is addressed using the existing non-negative subspace pursuit method, enabling the convolutional kernel to capture temporal correlations and patterns. To evaluate the proposed model, we apply it to several real-world time series datasets. On the multidimensional rideshare and taxi trip data from New York City and Chicago, the convolutional kernels reveal interpretable local correlations and cyclical patterns, such as weekly seasonality. In the context of multidimensional fluid flow data, both local and nonlocal correlations captured by the convolutional kernels can reinforce tensor factorization, leading to performance improvements in fluid flow reconstruction tasks. Thus, this study lays an insightful foundation for automatically learning convolutional kernels from time series data, with an emphasis on interpretability through sparsity and non-negativity constraints., Comment: 11 pages, 7 figures

Transportation mode share analysis is important to various real-world transportation tasks as it helps researchers understand the travel behaviors and choices of passengers. A typical example is the prediction of communities' travel mode share by accounting for their sociodemographics like age, income, etc., and travel modes' attributes (e.g. travel cost and time). However, there exist only limited efforts in integrating the structure of the urban built environment, e.g., road networks, into the mode share models to capture the impacts of the built environment. This task usually requires manual feature engineering or prior knowledge of the urban design features. In this study, we propose deep hybrid models (DHM), which directly combine road networks and sociodemographic features as inputs for travel mode share analysis. Using graph embedding (GE) techniques, we enhance travel demand models with a more powerful representation of urban structures. In experiments of mode share prediction in Chicago, results demonstrate that DHM can provide valuable spatial insights into the sociodemographic structure, improving the performance of travel demand models in estimating different mode shares at the city level. Specifically, DHM improves the results by more than 20\% while retaining the interpretation power of the choice models, demonstrating its superiority in interpretability, prediction accuracy, and geographical insights., Comment: 29 pages

This paper addresses the pressing challenge of urban mobility in the context of growing urban populations, changing demand patterns for urban mobility, and emerging technologies like Mobility-on-Demand (MoD) platforms and Autonomous Vehicle (AV). As urban areas swell and demand pattern changes, the integration of Autonomous Mobility-on-Demand (AMoD) systems with existing public transit (PT) networks presents great opportunities to enhancing urban mobility. We propose a novel optimization framework for solving the Transit-Centric Multimodal Urban Mobility with Autonomous Mobility-on-Demand (TCMUM-AMoD) at scale. The system operator (public transit agency) determines the network design and frequency settings of the PT network, fleet sizing and allocations of AMoD system, and the pricing for using the multimodal system with the goal of minimizing passenger disutility. Passengers' mode and route choice behaviors are modeled explicitly using discrete choice models. A first-order approximation algorithm is introduced to solve the problem at scale. Using a case study in Chicago, we showcase the potential to optimize urban mobility across different demand scenarios. To our knowledge, ours is the first paper to jointly optimize transit network design, fleet sizing, and pricing for the multimodal mobility system while considering passengers' mode and route choices., Comment: 31 Pages, 11 figures

The best way to treat chronic hepatitis B is with pegylated interferon alone or with oral antiviral drugs. There is limited research comparing the renal safety of entecavir and tenofovir when used with pegylated interferon. This study will compare changes in renal function in chronic hepatitis B patients treated with pegylated interferon and either entecavir or tenofovir. The study included a cohort of 836 patients with chronic hepatitis B (CHB) who received treatment with pegylated interferon (IFN) either alone or in combination with entecavir (ETV) and tenofovir (TDF) between the years 2018 and 2021. Of these patients, 713 were included in a matched analysis comparing outcomes between those who were cured and those who were uncured, while 123 patients received IFN alone as a control group for comparison with the ETV and TDF treatment groups. The primary outcome measured was the change in renal function, specifically estimated glomerular filtration rate (eGFR), cystatin C (CysC), and inorganic phosphorus (IPHOS). Patients were categorized into stage 1 or stage 2 based on a baseline eGFR of less than 90 ml/min/m^2 Results: 125 CHB patients were matched 1:1 in both the combined treatment and cured groups. Baseline eGFR, CysC, and IPHOS levels were similar between the groups. Renal function in stage 1 and stage 2 groups showed a decreasing trend at 48 weeks after an initial increase.Correlation analysis showed significant relationships between changes in ALT and eGFR values at 12 weeks in both non-cured and cured groups. Conclusions: Over the 48-week duration of combined treatment in patients with chronic hepatitis B (CHB), it was found that both Tenofovir Disoproxil Fumarate (TDF) and Entecavir (ETV) did not lead to an increase in renal injury., Comment: Over the 48-week duration of combined treatment in patients with chronic hepatitis B (CHB), it was found that both Tenofovir Disoproxil Fumarate (TDF) and Entecavir (ETV) did not lead to an increase in renal injury

Citywalk, a recently popular form of urban travel, requires genuine personalization and understanding of fine-grained requests compared to traditional itinerary planning. In this paper, we introduce the novel task of Open-domain Urban Itinerary Planning (OUIP), which generates personalized urban itineraries from user requests in natural language. We then present ITINERA, an OUIP system that integrates spatial optimization with large language models to provide customized urban itineraries based on user needs. This involves decomposing user requests, selecting candidate points of interest (POIs), ordering the POIs based on cluster-aware spatial optimization, and generating the itinerary. Experiments on real-world datasets and the performance of the deployed system demonstrate our system's capacity to deliver personalized and spatially coherent itineraries compared to current solutions. Source codes of ITINERA are available at https://github.com/YihongT/ITINERA.

Discrete choice models (DCMs) are the canonical methods for travel behavior modeling and prediction. However, in many scenarios, the collected data for DCMs are subject to measurement errors. Previous studies on measurement errors mostly focus on "better estimating model parameters" with training data. In this study, we focus on "better predicting new samples' behavior" when there are measurement errors in testing data. To this end, we propose a robust discrete choice model framework that is able to account for data uncertainties in both features and labels. The model is based on robust optimization theory that minimizes the worst-case loss over a set of uncertainty data scenarios. Specifically, for feature uncertainties, we assume that the $\ell_p$-norm of the measurement errors in features is smaller than a pre-established threshold. We model label uncertainties by limiting the number of mislabeled choices to at most $\Gamma$. Based on these assumptions, we derive a tractable robust counterpart for robust-feature and robust-label DCM models. The derived robust-feature binary logit (BNL) and the robust-label multinomial logit (MNL) models are exact. However, the formulation for the robust-feature MNL model is an approximation of the exact robust optimization problem. The proposed models are validated in a binary choice data set and a multinomial choice data set, respectively. Results show that the robust models (both features and labels) can outperform the conventional BNL and MNL models in prediction accuracy and log-likelihood. We show that the robustness works like "regularization" and thus has better generalizability.

The rapid growth of the ride-hailing industry has revolutionized urban transportation worldwide. Despite its benefits, equity concerns arise as underserved communities face limited accessibility to affordable ride-hailing services. A key issue in this context is the vehicle rebalancing problem, where idle vehicles are moved to areas with anticipated demand. Without equitable approaches in demand forecasting and rebalancing strategies, these practices can further deepen existing inequities. In the realm of ride-hailing, three main facets of fairness are recognized: algorithmic fairness, fairness to drivers, and fairness to riders. This paper focuses on enhancing both algorithmic and rider fairness through a novel vehicle rebalancing method. We introduce an approach that combines a Socio-Aware Spatial-Temporal Graph Convolutional Network (SA-STGCN) for refined demand prediction and a fairness-integrated Matching-Integrated Vehicle Rebalancing (MIVR) model for subsequent vehicle rebalancing. Our methodology is designed to reduce prediction discrepancies and ensure equitable service provision across diverse regions. The effectiveness of our system is evaluated using simulations based on real-world ride-hailing data. The results suggest that our proposed method enhances both accuracy and fairness in forecasting ride-hailing demand, ultimately resulting in more equitable vehicle rebalancing in subsequent operations. Specifically, the algorithm developed in this study effectively reduces the standard deviation and average customer wait times by 6.48% and 0.49%, respectively. This achievement signifies a beneficial outcome for ride-hailing platforms, striking a balance between operational efficiency and fairness., Comment: 31 pages, 6 figures

Travel behavior prediction is a fundamental task in transportation demand management. The conventional methods for travel behavior prediction rely on numerical data to construct mathematical models and calibrate model parameters to represent human preferences. Recent advancement in large language models (LLMs) has shown great reasoning abilities to solve complex problems. In this study, we propose to use LLMs to predict travel behavior with prompt engineering without data-based parameter learning. Specifically, we carefully design our prompts that include 1) task description, 2) travel characteristics, 3) individual attributes, and 4) guides of thinking with domain knowledge, and ask the LLMs to predict an individual's travel behavior and explain the results. We select the travel mode choice task as a case study. Results show that, though no training samples are provided, LLM-based predictions have competitive accuracy and F1-score as canonical supervised learning methods such as multinomial logit, random forest, and neural networks. LLMs can also output reasons that support their prediction. However, though in most of the cases, the output explanations are reasonable, we still observe cases that violate logic or with hallucinations.

Transit riders' feedback provided in ridership surveys, customer relationship management (CRM) channels, and in more recent times, through social media is key for transit agencies to better gauge the efficacy of their services and initiatives. Getting a holistic understanding of riders' experience through the feedback shared in those instruments is often challenging, mostly due to the open-ended, unstructured nature of text feedback. In this paper, we propose leveraging traditional transit CRM feedback to develop and deploy a transit-topic-aware large language model (LLM) capable of classifying open-ended text feedback to relevant transit-specific topics. First, we utilize semi-supervised learning to engineer a training dataset of 11 broad transit topics detected in a corpus of 6 years of customer feedback provided to the Washington Metropolitan Area Transit Authority (WMATA). We then use this dataset to train and thoroughly evaluate a language model based on the RoBERTa architecture. We compare our LLM, MetRoBERTa, to classical machine learning approaches utilizing keyword-based and lexicon representations. Our model outperforms those methods across all evaluation metrics, providing an average topic classification accuracy of 90%. Finally, we provide a value proposition of this work demonstrating how the language model, alongside additional text processing tools, can be applied to add structure to open-ended text sources of feedback like Twitter. The framework and results we present provide a pathway for an automated, generalizable approach for ingesting, visualizing, and reporting transit riders' feedback at scale, enabling agencies to better understand and improve customer experience.

High-resolution location ("heartbeat") data of transit fleet vehicles is a relatively new data source for many transit agencies. On its surface, the heartbeat data can provide a wealth of information about all operational details of a recorded transit vehicle trip, from its location trajectory to its speed and acceleration profiles. Previous studies have mainly focused on decomposing the total trip travel time into different components by vehicle state and then extracting measures of delays to draw conclusions on the performance of a transit route. This study delves into the task of reconstructing a complete, continuous and smooth transit vehicle trajectory from the heartbeat data that allows for the extraction of operational information of a bus at any point in time into its trip. Using only the latitude, longitude, and timestamp fields of the heartbeat data, the authors demonstrate that a continuous, smooth, and monotonic vehicle trajectory can be reconstructed using local regression in combination with monotonic cubic spline interpolation. The resultant trajectory can be used to evaluate transit performance and identify locations of bus delay near infrastructure such as traffic signals, pedestrian crossings, and bus stops., Comment: 7 pages, to be published in IEEE ITSC-2023

Traffic data serves as a fundamental component in both research and applications within intelligent transportation systems. However, real-world transportation data, collected from loop detectors or similar sources, often contains missing values (MVs), which can adversely impact associated applications and research. Instead of discarding this incomplete data, researchers have sought to recover these missing values through numerical statistics, tensor decomposition, and deep learning techniques. In this paper, we propose an innovative deep learning approach for imputing missing data. A graph attention architecture is employed to capture the spatial correlations present in traffic data, while a bidirectional neural network is utilized to learn temporal information. Experimental results indicate that our proposed method outperforms all other benchmark techniques, thus demonstrating its effectiveness., Comment: Accepted by IEEE-ITSC 2023

Remote work has expanded dramatically since 2020, upending longstanding travel patterns and behavior. More fundamentally, the flexibility for remote workers to choose when and where to work has created much stronger connections between travel behavior and organizational behavior. This paper uses a large and comprehensive monthly longitudinal survey over nearly three years to identify new trends in work location choice, mode choice and departure time of remote workers. The travel behavior of remote workers is found to be highly associated with employer characteristics, task characteristics, employer remote work policies, coordination between colleagues and attitudes towards remote work. Approximately one third of all remote work hours are shown to take place outside of the home, accounting for over one third of all commuting trips. These commutes to "third places" are shorter, less likely to occur during peak periods, and more likely to use sustainable travel modes than commutes to an employer's primary workplace. Hybrid work arrangements are also associated with a greater number of non-work trips than fully remote and fully in-person arrangements. Implications of this research for policy makers, shared mobility provides and land use planning are discussed.

COVID-19 has disrupted society and changed how people learn, work and live. The availability of vaccines in the spring of 2021, however, led to a gradual return of many pre-pandemic activities in Massachusetts in the fall of 2021. Leveraging data that were collected using a map-based survey tool in the Greater Boston area in the fall of 2021, this study explores changes in travel behavior due to COVID-19 and investigates the underlying factors contributing to these changes. First, a structural equation modeling technique is developed to capture the interactions between various travel choices, including working from home, travel mode use and change in car ownership. Moreover, attitudinal factors such as risk perceptions and attitudes towards WFH are incorporated into the framework to explain behavior changes. Second, a discrete choice modeling approach is taken to study shifts in commuting mode choices in the fall of 2021. The results show that in the fall of 2021, people became more likely to use their cars to commute, and for those who bought cars during the pandemic, they tended to work on-site more. Our findings can provide planners and policymakers with information upon which to base travel demand management decisions in the post-pandemic era.

Short-term demand forecasting for on-demand ride-hailing services is one of the fundamental issues in intelligent transportation systems. However, previous travel demand forecasting research predominantly focused on improving prediction accuracy, ignoring fairness issues such as systematic underestimations of travel demand in disadvantaged neighborhoods. This study investigates how to measure, evaluate, and enhance prediction fairness between disadvantaged and privileged communities in spatial-temporal demand forecasting of ride-hailing services. A two-pronged approach is taken to reduce the demand prediction bias. First, we develop a novel deep learning model architecture, named socially aware neural network (SA-Net), to integrate the socio-demographics and ridership information for fair demand prediction through an innovative socially-aware convolution operation. Second, we propose a bias-mitigation regularization method to mitigate the mean percentage prediction error gap between different groups. The experimental results, validated on the real-world Chicago Transportation Network Company (TNC) data, show that the de-biasing SA-Net can achieve better predictive performance in both prediction accuracy and fairness. Specifically, the SA-Net improves prediction accuracy for both the disadvantaged and privileged groups compared with the state-of-the-art models. When coupled with the bias mitigation regularization method, the de-biasing SA-Net effectively bridges the mean percentage prediction error gap between the disadvantaged and privileged groups, and also protects the disadvantaged regions against systematic underestimation of TNC demand. Our proposed de-biasing method can be adopted in many existing short-term travel demand estimation models, and can be utilized for various other spatial-temporal prediction tasks such as crime incidents predictions.

Classical demand modeling analyzes travel behavior using only low-dimensional numeric data (i.e. sociodemographics and travel attributes) but not high-dimensional urban imagery. However, travel behavior depends on the factors represented by both numeric data and urban imagery, thus necessitating a synergetic framework to combine them. This study creates a theoretical framework of deep hybrid models with a crossing structure consisting of a mixing operator and a behavioral predictor, thus integrating the numeric and imagery data into a latent space. Empirically, this framework is applied to analyze travel mode choice using the MyDailyTravel Survey from Chicago as the numeric inputs and the satellite images as the imagery inputs. We found that deep hybrid models outperform both the traditional demand models and the recent deep learning in predicting the aggregate and disaggregate travel behavior with our supervision-as-mixing design. The latent space in deep hybrid models can be interpreted, because it reveals meaningful spatial and social patterns. The deep hybrid models can also generate new urban images that do not exist in reality and interpret them with economic theory, such as computing substitution patterns and social welfare changes. Overall, the deep hybrid models demonstrate the complementarity between the low-dimensional numeric and high-dimensional imagery data and between the traditional demand modeling and recent deep learning. It generalizes the latent classes and variables in classical hybrid demand models to a latent space, and leverages the computational power of deep learning for imagery while retaining the economic interpretability on the microeconomics foundation.

Recent studies have significantly improved the prediction accuracy of travel demand using graph neural networks. However, these studies largely ignored uncertainty that inevitably exists in travel demand prediction. To fill this gap, this study proposes a framework of probabilistic graph neural networks (Prob-GNN) to quantify the spatiotemporal uncertainty of travel demand. This Prob-GNN framework is substantiated by deterministic and probabilistic assumptions, and empirically applied to the task of predicting the transit and ridesharing demand in Chicago. We found that the probabilistic assumptions (e.g. distribution tail, support) have a greater impact on uncertainty prediction than the deterministic ones (e.g. deep modules, depth). Among the family of Prob-GNNs, the GNNs with truncated Gaussian and Laplace distributions achieve the highest performance in transit and ridesharing data. Even under significant domain shifts, Prob-GNNs can predict the ridership uncertainty in a stable manner, when the models are trained on pre-COVID data and tested across multiple periods during and after the COVID-19 pandemic. Prob-GNNs also reveal the spatiotemporal pattern of uncertainty, which is concentrated on the afternoon peak hours and the areas with large travel volumes. Overall, our findings highlight the importance of incorporating randomness into deep learning for spatiotemporal ridership prediction. Future research should continue to investigate versatile probabilistic assumptions to capture behavioral randomness, and further develop methods to quantify uncertainty to build resilient cities.

Ridesharing is recognized as one of the key pathways to sustainable urban mobility. With the emergence of Transportation Network Companies (TNCs) such as Uber and Lyft, the ridesharing market has become increasingly fragmented in many cities around the world, leading to efficiency loss and increased traffic congestion. While an integrated ridesharing market (allowing sharing across TNCs) can improve the overall efficiency, how such benefits may vary across TNCs based on actual market characteristics is still not well understood. In this study, we extend a shareability network framework to quantify and explain the efficiency benefits of ridesharing market integration using available TNC trip records. Through a case study in Manhattan, New York City, the proposed framework is applied to analyze a real-world ridesharing market with 3 TNCs$-$Uber, Lyft, and Via. It is estimated that a perfectly integrated market in Manhattan would improve ridesharing efficiency by 13.3%, or 5% of daily TNC vehicle hours traveled. Further analysis reveals that (1) the efficiency improvement is negatively correlated with the overall demand density and inter-TNC spatiotemporal unevenness (measured by network modularity), (2) market integration would generate a larger efficiency improvement in a competitive market, and (3) the TNC with a higher intra-TNC demand concentration (measured by clustering coefficient) would benefit less from market integration. As the uneven benefits may deter TNCs from collaboration, we also illustrate how to quantify each TNC's marginal contribution based on the Shapley value, which can be used to ensure equitable profit allocation. These results can help market regulators and business alliances to evaluate and monitor market efficiency and dynamically adjust their strategies, incentives, and profit allocation schemes to promote market integration and collaboration.

Urban air mobility (UAM) has the potential to revolutionize transportation in metropolitan areas, providing a new mode of transportation that could alleviate congestion and improve accessibility. However, the integration of UAM into existing transportation systems is a complex task that requires a thorough understanding of its impact on traffic flow and capacity. In this paper, we conduct a survey to investigate the current state of research on UAM in metropolitan-scale traffic using simulation techniques. We identify key challenges and opportunities for the integration of UAM into urban transportation systems, including impacts on existing traffic patterns and congestion; safety analysis and risk assessment; potential economic and environmental benefits; and the development of shared infrastructure and routes for UAM and ground-based transportation. We also discuss the potential benefits of UAM, such as reduced travel times and improved accessibility for underserved areas. Our survey provides a comprehensive overview of the current state of research on UAM in metropolitan-scale traffic using simulation and highlights key areas for future research and development.

Understanding passengers' path choice behavior in urban rail systems is a prerequisite for effective operations and planning. This paper attempts bridging the gap by proposing a probabilistic approach to infer passengers' path choice behavior in urban rail systems using a large-scale smart card data. The model uses latent classes and panel effects to capture passengers' implicit behavior heterogeneity and longitudinal correlations, key research gaps in big data driven behavior studies. We formulate the probability of each individual's arrival time at a destination based on their path choice behavior, and estimate corresponding path choice model parameters as a maximum likelihood estimation problem. The original likelihood function is intractable due to the exponential computation complexity. We derive a tractable likelihood function and propose a numerical integral approach to efficiently estimate the model. Also, we propose a method to calculate the t-statistic of the estimated choice parameters based on the numerically estimated Hessian matrix and Cramer-Rao bound (the lower bound on the coefficient variance). Case studies using synthetic data validate the model performance and its robustness against parameter initialization and input errors, and highlight the importance of incorporating crowding impact in path choice estimation. Applications using actual data from the Mass Transit Railway, Hong Kong reveal two latent groups of passengers: time-sensitive (TS) and comfort-aware (CA). TS passengers are those who are more likely to choose paths with short travel times. Most of them are regular commuters with high travel frequency and less schedule flexibility. CA passengers care more about the travel comfort experience and choose paths with less walking and waiting times. The proposed approach is data-driven and general to accommodate other discrete choice structures.

In last-mile delivery, drivers frequently deviate from planned delivery routes because of their tacit knowledge of the road and curbside infrastructure, customer availability, and other characteristics of the respective service areas. Hence, the actual stop sequences chosen by an experienced human driver may be potentially preferable to the theoretical shortest-distance routing under real-life operational conditions. Thus, being able to predict the actual stop sequence that a human driver would follow can help to improve route planning in last-mile delivery. This paper proposes a pair-wise attention-based pointer neural network for this prediction task using drivers' historical delivery trajectory data. In addition to the commonly used encoder-decoder architecture for sequence-to-sequence prediction, we propose a new attention mechanism based on an alternative specific neural network to capture the local pair-wise information for each pair of stops. To further capture the global efficiency of the route, we propose a new iterative sequence generation algorithm that is used after model training to identify the first stop of a route that yields the lowest operational cost. Results from an extensive case study on real operational data from Amazon's last-mile delivery operations in the US show that our proposed method can significantly outperform traditional optimization-based approaches and other machine learning methods (such as the Long Short-Term Memory encoder-decoder and the original pointer network) in finding stop sequences that are closer to high-quality routes executed by experienced drivers in the field. Compared to benchmark models, the proposed model can increase the average prediction accuracy of the first four stops from around 0.2 to 0.312, and reduce the disparity between the predicted route and the actual route by around 15%.

Commuting is an important part of daily life. With the gradual recovery from COVID-19 and more people returning to work from the office, the transmission of COVID-19 during commuting becomes a concern. Recent emerging mobility services (such as ride-hailing and bike-sharing) further deteriorate the infection risks due to shared vehicles or spaces during travel. Hence, it is important to quantify the infection risks in commuting. This paper proposes a probabilistic framework to estimate the risk of infection during an individual's commute considering different travel modes, including public transit, ride-share, bike, and walking. The objective is to evaluate the probability of infection as well as the estimation errors (i.e., uncertainty quantification) given the origin-destination (OD), departure time, and travel mode. We first define a general trip planning function to generate trip trajectories and probabilities of choosing different paths according to the OD, departure time, and travel mode. Then, we consider two channels of infections: 1) infection by close contact and 2) infection by touching surfaces. The infection risks are calculated on a trip segment basis. Different sources of data (such as smart card data, travel surveys, and population data) are used to estimate the potential interactions between the individual and the infectious environment. The model is implemented in the MIT community as a case study. We evaluate the commute infection risks for employees and students. Results show that most of the individuals have an infection probability close to zero. The maximum infection probability is around 0.8%, implying that the probability of getting infected during the commuting process is low. Individuals with larger travel distances, traveling in transit, and traveling during peak hours are more likely to get infected.

This paper proposes a stochastic framework to evaluate the performance of public transit systems under short random service suspensions. We aim to derive closed-form formulations of the mean and variance of the queue length and waiting time. A bulk-service queue model is adopted to formulate the queuing behavior in the system. The random service suspension is modeled as a two-state (disruption and normal) Markov process. We prove that headway is distributed as the difference between two compound Poisson exponential random variables. The distribution is used to specify the mean and variance of queue length and waiting time at each station with analytical formulations. The closed-form stability condition of the system is also derived, implying that the system is more likely to be unstable with high incident rates and long incident duration. The proposed model is implemented on a bus network. Results show that higher incident rates and higher average incident duration will increase both the mean and variance of queue length and waiting time, which are consistent with the theoretical analysis. Crowding stations are more vulnerable to random service suspensions. The theoretical results are validated with a simulation model, showing consistency between the two outcomes.

This study proposes a mixed-integer programming formulation to model the individual-based path (IPR) recommendation problem during public transit service disruptions with the objective of minimizing system travel time and respecting passengers' path choice preferences. Passengers' behavior uncertainty in path choices given recommendations is also considered. We model the behavior uncertainty based on the passenger's prior preferences and posterior path choice probability distribution with two new concepts: epsilon-feasibility and Gamma-concentration, which control the mean and variance of path flows in the optimization problem. We show that these two concepts can be seen as a way of approximating the recourse function (expected system travel time) in a two-stage stochastic optimization. It is proved that these two concepts help to bound the difference between the approximated recourse function and the exact one. Additional theoretical analysis shows that epsilon-feasibility and Gamma-concentration can be seen as an approximation of expectation and chance constraints in a typical stochastic optimization formulation, respectively. The proposed IPR problem with behavior uncertainty is solved efficiently with Benders decomposition. The model is implemented in the Chicago Transit Authority (CTA) system with a real-world urban rail disruption as the case study. Results show that the proposed IPR model significantly reduces the average travel times compared to the status quo and outperforms the capacity-based benchmark path recommendation strategy.

Accurate travel time estimation is paramount for providing transit users with reliable schedules and dependable real-time information. This paper is the first to utilize roadside urban imagery for direct transit travel time prediction. We propose and evaluate an end-to-end framework integrating traditional transit data sources with a roadside camera for automated roadside image data acquisition, labeling, and model training to predict transit travel times across a segment of interest. First, we show how the GTFS real-time data can be utilized as an efficient activation mechanism for a roadside camera unit monitoring a segment of interest. Second, AVL data is utilized to generate ground truth labels for the acquired images based on the observed transit travel time percentiles across the camera-monitored segment during the time of image acquisition. Finally, the generated labeled image dataset is used to train and thoroughly evaluate a Vision Transformer (ViT) model to predict a discrete transit travel time range (band). The results illustrate that the ViT model is able to learn image features and contents that best help it deduce the expected travel time range with an average validation accuracy ranging between 80%-85%. We assess the interpretability of the ViT model's predictions and showcase how this discrete travel time band prediction can subsequently improve continuous transit travel time estimation. The workflow and results presented in this study provide an end-to-end, scalable, automated, and highly efficient approach for integrating traditional transit data sources and roadside imagery to improve the estimation of transit travel duration. This work also demonstrates the value of incorporating real-time information from computer-vision sources, which are becoming increasingly accessible and can have major implications for improving operations and passenger real-time information., Comment: Final revised preprint

There are substantial differences in travel behavior by gender on public transit. Studies have concluded that these differences are largely attributable to household responsibilities typically falling disproportionately on women, leading to women being more likely to utilize transit for purposes referred to by the umbrella concept of "mobility of care". In contrast to past studies that have quantified the impact of gender using survey and qualitative data, we propose a novel data-driven workflow utilizing a combination of previously developed origin, destination, and transfer inference (ODX) based on individual transit fare card transactions, name-based gender inference, and geospatial analysis as a framework to identify mobility of care trip making. We apply this framework to data from the Washington Metropolitan Area Transit Authority (WMATA). Analyzing data from millions of journeys conducted in the first quarter of 2019, the results of this study show that our proposed workflow can identify mobility of care travel behavior, detecting times and places of interest where the share of women travelers in an equally-sampled subset (on basis of inferred gender) of transit users is 10% - 15% higher than that of men. The workflow presented in this study provides a blueprint for combining transit origin-destination data, inferred customer demographics, and geospatial analyses enabling public transit agencies to assess, at the fare card level, the gendered impacts of different policy and operational decisions., Comment: Final revised version for journal publication

Origin-Destination (O-D) travel demand prediction is a fundamental challenge in transportation. Recently, spatial-temporal deep learning models demonstrate the tremendous potential to enhance prediction accuracy. However, few studies tackled the uncertainty and sparsity issues in fine-grained O-D matrices. This presents a serious problem, because a vast number of zeros deviate from the Gaussian assumption underlying the deterministic deep learning models. To address this issue, we design a Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network (STZINB-GNN) to quantify the uncertainty of the sparse travel demand. It analyzes spatial and temporal correlations using diffusion and temporal convolution networks, which are then fused to parameterize the probabilistic distributions of travel demand. The STZINB-GNN is examined using two real-world datasets with various spatial and temporal resolutions. The results demonstrate the superiority of STZINB-GNN over benchmark models, especially under high spatial-temporal resolutions, because of its high accuracy, tight confidence intervals, and interpretable parameters. The sparsity parameter of the STZINB-GNN has physical interpretation for various transportation applications., Comment: Accepted by KDD 2022