Jinhua Zhao

Verified

Jinhua verified their affiliation via an institutional email.

Learn more

Verified

Jinhua verified their affiliation via an institutional email.

Learn more

• Doctor of Philosophy
• Professor (Full) at Massachusetts Institute of Technology

Simulating society with large language models (LLMs), we argue, requires more than generating plausible behavior -- it demands cognitively grounded reasoning that is structured, revisable, and traceable. LLM-based agents are increasingly used to emulate individual and group behavior -- primarily through prompting and supervised fine-tuning. Yet the...

Spatiotemporal systems are ubiquitous in a large number of scientific areas, representing underlying knowledge and patterns in the data. Here, a fundamental question usually arises as how to understand and characterize these spatiotemporal systems with a certain data-driven machine learning framework. In this work, we introduce an unsupervised patt...

Urban and transportation research has long sought to uncover statistically meaningful relationships between key variables and societal outcomes such as road safety, to generate actionable insights that guide the planning, development, and renewal of urban and transportation systems. However, traditional workflows face several key challenges: (1) re...

Urban design is a multifaceted process that demands careful consideration of site-specific constraints and collaboration among diverse professionals and stakeholders. The advent of generative artificial intelligence (GenAI) offers transformative potential by improving the efficiency of design generation and facilitating the communication of design...

Generative AI offers new opportunities for automating urban planning by creating site-specific urban layouts and enabling flexible design exploration. However, existing approaches often struggle to produce realistic and practical designs at scale. Therefore, we adapt a state-of-the-art Stable Diffusion model, extended with ControlNet, to generate h...

Urban causal research is essential for understanding the complex dynamics of cities and informing evidence-based policies. However, it is challenged by the inefficiency and bias of hypothesis generation, barriers to multimodal data complexity, and the methodological fragility of causal experimentation. Recent advances in large language models (LLMs...

Travel demand modeling has shifted from aggregated trip-based models to behavior-oriented activity-based models because daily trips are essentially driven by human activities. To analyze the sequential activity-travel decisions, deep inverse reinforcement learning (DIRL) has proven effective in learning the decision mechanisms by approximating a re...

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 r...

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 ch...

Highlights What are the main findings? A novel RL framework is proposed for bus operations, integrating three high-level actions: holding, skipping, and turning around to reduce passenger waiting times. The model incorporates LSTM to capture both Markov and non-Markov processes, enhancing decision-making based on past actions and future predictions...

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, much of the spatial reasoning in these tasks occurs in two-d...

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 uti...

Public transit systems are the backbone of urban mobility systems in the era of urbanization. The design of transit schedules is important for the efficient and sustainable operation of public transit. However, limited studies have considered demand uncertainties when designing transit schedules. To better address demand uncertainty issues inherent...

We present Vertiport-informed Surrogate-Based Optimization with Machine Learning Surrogates (VinS), a novel framework for solving the vertiport location problem for urban air mobility operations. The primary focus of this work is on the optimization of vertiport locations to facilitate efficient urban air transportation. Our framework helps choose...

Electric vehicle charging stations (EVCS) are essential for promoting cleaner transportation by facilitating electric vehicle recharging. This study explores their broader economic impact on nearby businesses, analyzing data from over 4000 EVCS and 140,000 business establishments in California. Results show that installing one EVCS boosts annual sp...

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...

Quantifying uncertainty is crucial for robust and reliable predictions. However, existing spatiotemporal deep learning mostly fo-cuses on deterministic prediction, overlooking the inherent uncertainty in such prediction. Particularly, highly-granular spatiotempo-ral datasets are often sparse, posing extra challenges in prediction and uncertainty qu...

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 unc...

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. trave...

Remote work's potential as a sustainable mobility solution has garnered attention, particularly due to its widespread adoption during the COVID-19 pandemic. Our study systematically examines the impacts of remote work on vehicle-miles traveled (VMT) and transit ridership in the United States from April 2020 to October 2022. We find that using the p...

Accurate travel time estimation is paramount for providing transit users with reliable schedules and dependable real-time information. This work is the first to utilize roadside urban imagery to aid transit agencies and practitioners in improving travel time prediction. We propose and evaluate an end-to-end framework integrating traditional transit...

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...

The bus control problem that combines holding and stop-skipping strategies is formulated as a multi-agent reinforcement learning (MARL) problem. Traditional MARL methods, designed for settings with joint action-taking, are incompatible with the asynchronous nature of at-stop control tasks. On the other hand, using a fully decentralized approach lea...

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...

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...

Previous work on misbehavior detection and trust management for Vehicle-to-Everything (V2X) communication security is effective in identifying falsified and malicious V2X data. Each vehicle in a given region can be a witness to report on the misbehavior of other nearby vehicles, which will then be added to a “blacklist.” However, there may not exis...

Studies in the literature have found significant differences in travel behavior by gender on public transit that are largely attributable to household and care responsibilities falling disproportionately on women. While the majority of studies have relied on survey and qualitative data to assess “mobility of care”, we propose a novel data-driven wo...

To combat congestion, promote sustainable forms of transportation, and support the public transit system, Chicago introduced a congestion pricing policy targeting transportation network company (TNC) services on January 6, 2020. This policy aimed to discourage single-occupant and peak-period TNC travel, particularly in high-congestion areas. Using...

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...

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...

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 neighbor...

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 unc...

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 cr...

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 rideshari...

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 theoret...

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...

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 d...

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 c...

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 su...

This is a two-part mixed methods study that investigated motivations for watching videos on mobile phones while driving. We make three theoretical contributions in this paper. First, we specifically examine watching videos on mobile phones while driving, whereas previous studies examine calling, texting, monitoring messages, and using apps. Second,...

Short-term demand forecasting for on-demand ride-hailing services is a fundamental issue in intelligent transportation systems. However, previous research predominantly focused on improving prediction accuracy, ignoring fairness issues such as systematic underestimations of travel demand in disadvantaged neighborhoods. This study investigates how t...

With millions of people using ride-hailing platforms for daily travel, estimated time of arrival (ETA) has become a significant problem in intelligent transportation systems and attracted considerable attention recently. Deep learning-based ETA methods have achieved promising results using massive spatial-temporal data. However, we find that the pr...

Accurate travel time estimation is paramount for providing transit users with reliable schedules and dependable real-time information. This paper proposes and evaluates a novel end-to-end framework for transit and roadside image data acquisition, labeling, and model training to predict transit travel times across a segment of interest. General Tran...

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 c...

This paper proposes an ex post path choice estimation framework for urban rail systems using an aggregated time-space hypernetwork approach. We aim to infer the actual passenger flow distribution in an urban rail system for any historical day using the observed automated fare collection (AFC) data. By incorporating a schedule-based dynamic transit...

Despite many studies on trip inference using call detail record (CDR) data, a fundamental understanding of their limitations is lacking. In particular, because of the sparse nature of CDR data, users may travel to a location without being revealed in the data, which we refer to as a hidden visit. The existence of hidden visits hinders our ability t...

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...

Previous studies have shown that the rider satisfaction on bus services vary between males and females. As women make a significant number of transit trips in developing countries nowadays, it is crucial to understand their perceptions and satisfactions towards different service aspects of public transit, thus to provide transit agencies with the g...

In mobility sharing markets, there are two conflicting principles: 1) the healthy competition between platforms, such as Uber and Lyft, and 2) economies of network scale, which leads to higher chances for trips to be matched, and thus higher efficiency. The status quo mobility sharing markets are either monopolistic or largely segmented with signif...

On-demand mobility sharing, provided by one or several transportation network companies (TNCs), is realized by real-time optimization algorithms to connect trips among tens of thousands of drivers and fellow passengers. In a market of mobility sharing comprised of TNCs, there are two competing principles, the economies of network scale and the heal...

The Braess's Paradox (BP) is the observation that adding one or more roads to the existing road network will counter-intuitively increase traffic congestion and slow down the overall traffic flow. Previously, the existence of the BP is modeled using the static traffic assignment model, which solves for the user equilibrium subject to network flow c...

This study proposes a probabilistic framework to infer passengers’ responses to unplanned urban rail service disruptions using smart card data in tap-in-only public transit systems. We first identify 19 possible response behaviors that passengers may have based on their decision-making times and locations (i.e, the stage of their trips when an inci...

When there are significant service disruptions in public transit systems, passengers usually need guidance to find alternative paths. This paper proposes a path recommendation model to mitigate the congestion during public transit disruptions. Passengers with different origin-destination and departure times are recommended with different paths such...

Many studies of the effect of remote work on travel demand assume that remote work takes place entirely at home. Recent evidence, however, shows that in the United States, remote workers are choosing to spend approximately one third of their remote work hours outside of the home at cafes, co-working spaces or the homes of friends and family. Commut...

When there are significant service disruptions in public transit systems, passengers usually need guidance to find alternative paths. This paper proposes a path recommendation model to mitigate the congestion during public transit disruptions. Passengers with different origin-destination and departure times are recommended with different paths such...

A gradual growth in flexible work over many decades has been suddenly and dramatically accelerated by the COVID-19 pandemic. The share of flexible work days in the United States is forecasted to grow from 4\% in 2018 to over 26\% by 2022. This rapid and unexpected shift in the nature of work will have a profound effect on the demand for, and supply...

This paper proposes a general unplanned incident analysis framework for public transit systems from the supply and demand sides using automated fare collection (AFC) and automated vehicle location (AVL) data. Specifically, on the supply side, we propose an incident-based network redundancy index to analyze the network's ability to provide alternati...

Rebalancing vacant vehicles is one of the most critical strategies in ride-hailing operations. An effective rebalancing strategy can significantly reduce empty miles traveled and reduce customer wait times by better matching supply and demand. While the supply (vehicles) is usually known to the system, future passenger demand is uncertain. There ar...

This paper proposes a general unplanned incident analysis framework for public transit systems from the supply and demand sides using automated fare collection (AFC) and automated vehicle location (AVL) data. Specifically, on the supply side, we propose an incident-based network redundancy index to analyze the network’s ability to provide alternati...

As Transportation Network Companies (TNCs) have expanded their role in U.S. cities recently, their services (i.e. ridehailing) have been subject to scrutiny for displacing public transit (PT) ridership. Previous studies have attempted to classify the relationship between transit and TNCs, though analysis has been limited by a lack of granular TNC t...

Estimating passengers’ door-to-door travel time, for journeys that combine walking and public transit, can be complex for large networks with many available path alternatives. Additional complications arise in tap-on only transit systems, where passengers alightings are not recorded. For one such system, the Chicago Transit Authority, this study co...

Urban leaders in areas with high air pollution often face the dual task of reducing pollution levels while educating the public about the health impacts of pollution and preventive measures. Transportation policies to cut motorized personal vehicle use are often a key part of pollution reduction efforts. One type of these policies is information in...

The implementation of Bus Rapid Transit (BRT) is intended to provide higher-quality services and significantly improve rider satisfaction. Previous studies have investigated rider satisfaction and its determinants to improve BRT services as well as the comparison between BRT and conventional bus/rail transit regarding the rider satisfaction. Howeve...

The concept of level of service (LOS) is meant to reflect user perception of the quality of service provided by a transportation facility or service. Although the LOS of bus rapid transit (BRT) has received considerable attention, the number of levels of service of BRT that a user can perceive still remains unclear. Therefore, in this paper, we add...

Although researchers increasingly adopt machine learning to model travel behavior, they predominantly focus on prediction accuracy, ignoring the ethical challenges embedded in machine learning algorithms. This study introduces an important missing dimension - computational fairness - to travel behavior analysis. We first operationalize computationa...

Although researchers increasingly adopt machine learning to model travel behavior, they predominantly focus on prediction accuracy, ignoring the ethical challenges embedded in machine learning algorithms. This study introduces an important missing dimension-computational fairness-to travel behavior analysis. It highlights the accuracy-fairness trad...

For decades, transportation researchers have used survey data to understand the factors that affect travel-related choices. Nowadays, travel surveys lay the foundation of travel behavior analysis for transportation modeling, planning, and policy-making. The development of information technology for urban sensing has enabled substantial improvements...

Individual mobility is driven by demand for activities with diverse spatiotemporal patterns, but existing methods for mobility prediction often overlook the underlying activity patterns. Knowledge of activity patterns can improve the performance and interpretability of existing individual mobility models, leading to more informed policy design and...

Many cities around the world have adopted dockless bike-sharing programs with the hope that this new service could enhance last-mile public transit connections. However, our understanding of the travel patterns using dockless bike sharing is still limited. To advance the knowledge on the new service, this study investigates mobility patterns of doc...

As autonomous vehicle (AV) technology advances, it is important to understand its potential demand and user characteristics. Literature from stated preference surveys find that attitudes and current travel behavior are as or more important than demographics in determining intention to purchase or use AVs. Yet to date no study has looked at how atti...

Demand for public transport has witnessed a steady growth over the last decade in many densely populated cities around the world. However, capacity has not always matched this increased demand. As such, passengers experience long waiting times and are denied boarding during the peak hours. Crowded platforms and the subsequent customer dissatisfacti...

Despite a large body of literature on trip inference using call detail record (CDR) data, a fundamental understanding of their limitations is lacking. In particular, because of the sparse nature of CDR data, users may travel to a location without being revealed in the data, which we refer to as a "hidden visit". The existence of hidden visits hinde...

The dynamic monitoring of home and workplace distribution is a fundamental building block for improving location-based service systems in fast-developing cities worldwide. Inferring these places is challenging; existing approaches rely on labor-intensive and untimely survey data or ad hoc heuristic assignment rules based on the frequency of appeara...