About

Jinhua Zhao is the Edward and Joyce Linde Associate Professor of City and Transportation Planning at MIT. His research focuses on shaping travel behavior, designing mobility systems, and reforming urban policies by integrating behavioral science and transportation technology. He develops methods to sense, predict, nudge, and regulate travel behavior and designs multimodal mobility systems that incorporate automated and shared mobility with public transport. Zhao sees transportation as a language to describe a person, characterize a city, and understand an institution, aiming to establish the behavioral foundation for transportation systems and policies. He directs the JTL Urban Mobility Lab and Transit Lab at MIT and leads long-term research collaborations with major transportation authorities and operators worldwide, including London, Chicago, Hong Kong, and Singapore. Zhao is also the co-director of the Mobility Systems Center of the MIT Energy Initiative and the director of the MIT Mobility Initiative. He enjoys working with students and is actively involved in advancing urban transportation planning and policy through his research and leadership roles.

Research topics

• Computer Science
• Data Mining
• Engineering
• Transport engineering
• Economics
• Computer Security
• Geography
• Artificial Intelligence
• Business
• Machine Learning
• Microeconomics
• Marketing
• Econometrics
• Finance
• Database
• Environmental health
• Medicine

Selected publications

• Risk-Controllable Multi-View Diffusion for Driving Scenario Generation

  ArXiv.org · 2026-03-12

  articleOpen accessSenior author

  Generating safety-critical driving scenarios is crucial for evaluating and improving autonomous driving systems, but long-tail risky situations are rarely observed in real-world data and difficult to specify through manual scenario design. Existing generative approaches typically treat risk as an after-the-fact label and struggle to maintain geometric consistency in multi-view driving scenes. We present RiskMV-DPO, a general and systematic pipeline for physically-informed, risk-controllable multi-view scenario generation. By integrating target risk levels with physically-grounded risk modeling, we autonomously synthesize diverse and high-stakes dynamic trajectories that serve as explicit geometric anchors for a diffusion-based video generator. To ensure spatial-temporal coherence and geometric fidelity, we introduce a geometry-appearance alignment module and a region-aware direct preference optimization (RA-DPO) strategy with motion-aware masking to focus learning on localized dynamic regions.Experiments on the nuScenes dataset show that RiskMV-DPO can freely generate a wide spectrum of diverse long-tail scenarios while maintaining state-of-the-art visual quality, improving 3D detection mAP from 18.17 to 30.50 and reducing FID to 15.70. Our work shifts the role of world models from passive environment prediction to proactive, risk-controllable synthesis, providing a scalable toolchain for the safety-oriented development of embodied intelligence.

  PublisherOA PDF

• From Creative Destruction to Architectural Construction: How EVs Reshape Industrial Regimes

  SSRN Electronic Journal · 2026-01-01

  preprintOpen accessSenior author
  PublisherDOI

• Risk-Controllable Multi-View Diffusion for Driving Scenario Generation

  arXiv (Cornell University) · 2026-03-12

  preprintOpen accessSenior author

  Generating safety-critical driving scenarios is crucial for evaluating and improving autonomous driving systems, but long-tail risky situations are rarely observed in real-world data and difficult to specify through manual scenario design. Existing generative approaches typically treat risk as an after-the-fact label and struggle to maintain geometric consistency in multi-view driving scenes. We present RiskMV-DPO, a general and systematic pipeline for physically-informed, risk-controllable multi-view scenario generation. By integrating target risk levels with physically-grounded risk modeling, we autonomously synthesize diverse and high-stakes dynamic trajectories that serve as explicit geometric anchors for a diffusion-based video generator. To ensure spatial-temporal coherence and geometric fidelity, we introduce a geometry-appearance alignment module and a region-aware direct preference optimization (RA-DPO) strategy with motion-aware masking to focus learning on localized dynamic regions.Experiments on the nuScenes dataset show that RiskMV-DPO can freely generate a wide spectrum of diverse long-tail scenarios while maintaining state-of-the-art visual quality, improving 3D detection mAP from 18.17 to 30.50 and reducing FID to 15.70. Our work shifts the role of world models from passive environment prediction to proactive, risk-controllable synthesis, providing a scalable toolchain for the safety-oriented development of embodied intelligence.

  PublisherDOI

• Remote work expands pathways to upward career mobility

  ArXiv.org · 2026-05-02

  articleOpen accessSenior author

  Geographic constraints have long structured access to high-growth career opportunities, concentrating upward mobility within a limited set of cities and organizations. The expansion of remote work potentially alters this opportunity structure by decoupling job matching from physical proximity, yet its implications for career mobility remain unclear. Using 48 million U.S. job transitions between 2020 and 2024 linked to employer-level measures of remote eligibility, we estimate how entering remote-eligible jobs shapes career outcomes at job transitions. Workers entering remote-eligible jobs experience significantly higher wage growth and higher rates of upward seniority mobility than comparable workers entering fully on-site roles. These transitions are also associated with greater cross-metropolitan job mobility and moves toward smaller, less prestigious employers. Importantly, effects are largest among lower-income workers and those originating from regions with limited high-skill opportunity density. Together, the findings indicate that remote work relaxes geographic constraints in job matching, reshaping the distribution of upward mobility across places and workers.

  PublisherOA PDF

• From street views to urban science: Discovering road safety factors with multimodal large language models

  Transportation Research Part C Emerging Technologies · 2026-04-16 · 1 citations

  articleOpen access

  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) reliance on human experts to propose hypotheses, which is time-consuming and prone to confirmation bias; (2) limited interpretability, particularly in deep learning approaches; and (3) underutilization of unstructured data that can encode critical urban context. Given these limitations, we propose a Multimodal Large Language Model (MLLM)-based approach for interpretable hypothesis inference, enabling the automated generation, evaluation, and refinement of hypotheses concerning urban context and road safety outcomes. Our method leverages MLLMs to craft safety-relevant questions for street view images (SVIs), extract interpretable embeddings from their responses, and apply them in regression-based statistical models. UrbanX supports iterative hypothesis testing and refinement, guided by statistical evidence such as coefficient significance, thereby enabling rigorous scientific discovery of previously overlooked correlations between urban design and safety. Experimental evaluations on Manhattan street segments demonstrate that our approach outperforms pretrained deep learning models while offering full interpretability. Beyond road safety, UrbanX can serve as a general-purpose framework for urban scientific discovery, extracting structured insights from unstructured urban data across diverse socioeconomic and environmental outcomes. This approach enhances model trustworthiness for policy applications and establishes a scalable, statistically grounded pathway for interpretable knowledge discovery in urban and transportation studies.

  PublisherDOI

• Trajectory-integrated accessibility analysis of public electric vehicle charging stations

  Sustainable Cities and Society · 2026-05-01

  articleOpen access
  PublisherOA PDFDOI

• SOD-YOLO: Enhancing YOLO-Based Detection of Small Objects in UAV Imagery

  ArXiv.org · 2025-07-17 · 1 citations

  preprintOpen accessSenior author

  Small object detection remains a challenging problem in the field of object detection. To address this challenge, we propose an enhanced YOLOv8-based model, SOD-YOLO. This model integrates an ASF mechanism in the neck to enhance multi-scale feature fusion, adds a Small Object Detection Layer (named P2) to provide higher-resolution feature maps for better small object detection, and employs Soft-NMS to refine confidence scores and retain true positives. Experimental results demonstrate that SOD-YOLO significantly improves detection performance, achieving a 36.1% increase in mAP$_{50:95}$ and 20.6% increase in mAP$_{50}$ on the VisDrone2019-DET dataset compared to the baseline model. These enhancements make SOD-YOLO a practical and efficient solution for small object detection in UAV imagery. Our source code, hyper-parameters, and model weights are available at https://github.com/iamwangxiaobai/SOD-YOLO.

  PublisherOA PDFDOI

• Individual Path Recommendation Under Public Transit Service Disruptions Considering Behavior Uncertainty

  Transportation Science · 2025-10-24

  articleSenior author

  Public transit passengers need guidance during service disruptions. This study proposes an individual-based path recommendation (IPR) model. The model decides which paths to recommend for each passenger with the objective of minimizing system travel time and respecting passengers’ path choice preferences. We assume the recommendations could affect passengers’ path choice probabilities, but their actual choices are uncertain. This behavior uncertainty makes the problem a stochastic optimization with decision-dependent distributions. We propose a single-point approximation method to eliminate the expectation operator by introducing two new concepts: [Formula: see text]-feasibility and [Formula: see text]-concentration, which control the mean and variance of path flows in the optimization problem. The approximation yields a tractable single-stage mixed integer linear formulation, which can be solved efficiently with Benders decomposition. The approximation gap is proved to be bounded from above. Additional theoretical analysis shows that [Formula: see text]-feasibility and [Formula: see text]-concentration are strongly connected to expectation and chance constraints in a typical stochastic optimization formulation, respectively. The model is implemented in a real-world case study using data from an urban rail disruption in the Chicago Transit Authority system and a synthetic case study with varied network sizes and incident locations. In the real-world case study, results show that the proposed IPR model reduces the average travel times in the system by 6.6% compared with the status quo and by 4.2% compared with a capacity-based benchmark model. In the synthetic case study, the proposed model shows 15.0%–1.8% lower system travel time compared with the capacity-based benchmark, depending on the network sizes and demand situations. Funding: This work was supported by the Chicago Transit Authority. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2025.0042 .

  PublisherDOI

• Generative AI for urban planning: Synthesizing satellite imagery via diffusion models

  Computers Environment and Urban Systems · 2025-09-04 · 7 citations

  article
  PublisherDOI

• The Pernicious Effects of Uncertainty on Municipal Climate Action

  Urban Affairs Review · 2025-06-19

  articleOpen accessSenior author

  How elected officials make policy in an uncertain context is insufficiently understood. To fill that gap, this research examines how much uncertainty impacts climate action in large U.S. cities. We sent a survey to all elected officials in U.S. cities with populations >100,000, querying their level of climate uncertainty and their support for climate policies. To analyze the results, we use a structural equation model with a robust and novel measure of climate uncertainty and then examine the direct and indirect effects of climate uncertainty on a policymakers’ propensity to support climate action. We find that municipal elected officials are generally supportive of climate action, though their support varies substantially based on their partisan affiliations and views about the appropriate role of government. Increased climate uncertainty diminishes support for action. These findings suggest the importance of communicating the robustness and co-benefits of climate policies.

  PublisherDOI

Frequent coauthors

• Shenhao Wang

  56 shared

• Haris N. Koutsopoulos

  53 shared

• Baichuan Mo

  41 shared

• Yu Shen

  Tongji University

  25 shared

• Yunhan Zheng

  25 shared

• Zhan Zhao

  23 shared

• Qingyi Wang

  21 shared

• Joanna Moody

  21 shared

Education

• PhD, Urban Studies and Planning

  Massachusetts Institute of Technology

  2009