Dingyi Zhuang

Dingyi Zhuang

Ph.D. in Transportation @ MIT


About me

I am a fourth-year Ph.D. student at MIT JTL Transit Lab supervised by Prof. Jinhua Zhao. I previously received my M.Eng degree at McGill University, supervised by Prof. Lijun Sun. Before that, I obtained my Bachelor’s degree in Mechanical Engineering from Shanghai Jiao Tong University and was a research assistant at National University of Singapore. My supervisors at two universities are Prof. Jiangang Jin and Prof. Lee Der-Horng respectively. Click here to view my up-to-date CV.

Research Interests

Bring AI techniques to transportation engineering and urban planning.

Urban:

  • Urban computing
  • Spatiotemporal data mining and pattern discovery
  • Travel behavior analysis

AI:

  • Graph neural network
  • Generative AI
  • Reinforcement learning
  • Trustworthy AI

Four particular questions I studied and try to connect together during my Ph.D.:

  1. Spatiotemporal data modeling: imputation, forecasting, kriging, and dynamic kriging. Particularly applying Graph Neural Networks.
  2. Uncertainty quantification: forecasting with prediction intervals (Baysian or Frequentist ways) and ensuring reliable prediction intervals
  3. Unstructured data integration and interpretation: images, virtual & physical networks, textual data
  4. Equity and social consideration: mitigating biases (e.g. fariness) in deep learning and AI for humand development

Publication

Journal

  • Xiaowei Gao, Xinke Jiang, James Haworth, Dingyi Zhuang, Shenhao Wang, Huanfa Chen, Stephen Law, Uncertainty-aware probabilistic graph neural networks for road-level traffic crash prediction, Accident Analysis and Prevention, 2024. doi

  • Xudong Wang, Yuankai Wu, Dingyi Zhuang, Lijun Sun. “Low-Rank Hankel Tensor Completion for Traffic Speed Estimation.” IEEE Transactions on Intelligent Transportation Systems doi

  • Fuqiang Liu, Jiawei Wang, Jingbo Tian, Dingyi Zhuang, Luis Miranda-Moreno, and Lijun Sun. “A Universal Framework of Spatiotemporal Bias Block for Long-Term Traffic Forecasting.” IEEE Transactions on Intelligent Transportation Systems doi description

  • Dingyi Zhuang, Siyu Hao, Lee Der-Horng, Jiangang Jin, “From compound word to metropolitan station: Semantic similarity analysis using smart card data”, Transportation Research Part C: Emerging Technology. PPT doi code description

  • Dingyi Zhuang, Jiangang Jin, Yifan Shen, Wei Jiang, “Understanding the bike sharing travel demand and cycle lane network: the case of Shanghai”, International Journal of Sustainable Transportation. PDF doi description

  • Qingyi Wang, Shenhao Wang, Dingyi Zhuang, Haris Koutsopoulos, Jinhua Zhao, “Uncertainty Quantification of Spatiotemporal Travel Demand with Probabilistic Graph Neural Networks”, in submission to IEEE Transactions on Intelligent Transportation Systems. doi

  • Yunhan Zheng, Qingyi Wang, Dingyi Zhuang, Shenhao Wang, Jinhua Zhao, “Fairness-enhancing deep learning for ride-hailing demand prediction”, IEEE Open Journal of Intelligent Transportation Systems. doi

Conference

CS + AI

  • Yihong Tang, Zhaokai Wang, Ao Qu, Yihao Yan, Kebing Hou, Dingyi Zhuang, Xiaotong Guo, Jinhua Zhao, Zhan Zhao, Wei Ma, ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning, The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024); The 13th International Workshop on Urban Computing (Urbcomp 2024). (Best Paper Award) paper

  • Dingyi Zhuang, Yuheng Bu, Guang Wang, Shenhao Wang, Jinhua Zhao, SAUC: Sparsity-Aware Uncertainty Calibration for Spatiotemporal Prediction with Graph Neural Networks, NeurIPS 2023 TGL Workshop (Best Paper Candidate) paper

  • Xinke Jiang, Dingyi Zhuang, Xianghui Zhang, Hao Chen, Jiayuan Luo, Xiaowei Gao, Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Prediction, *CIKM 2023. (In proceeding) paper

  • Dingyi Zhuang, Shenhao Wang, Haris Koutsopoulos, Jinhua Zhao, Uncertainty Quantification of Sparse Trip Demand Prediction with Spatial-Temporal Graph Neural Networks, The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD 2022). (Oral presentation) code doi description

  • Yuankai Wu, Dingyi Zhuang, Aurelie Labbe, Lijun Sun, Inductive graph neural networks for spatiotemporal kriging, Association for the Advancement of Artificial Intelligence 2021 (AAAI 2021). (Oral presentation) arXiv code description

Transportation and Urban Science

  • Dingyi Zhuang, Hanyong Xu, Xiaotong Guo, Yunhan Zheng, Jinhua Zhao, Mitigating Spatial Disparity in Urban Prediction Using Residual-Aware Spatiotemporal Graph Neural Networks: A Chicago Case Study, Transportation Research Board, 2025.

  • Xiaoyang Cao, Dingyi Zhuang, Shenhao Wang, Jinhua Zhao, Virtual Nodes Improve Long-term Traffic Prediction, Transportation Research Board, 2025.

  • Baichuan Mo, Hanyong Xu, Dingyi Zhuang, Ruoyun Ma, Xiaotong Guo, Jinhua Zhao, Large language models for travel behavior prediction, TRC-30, 2024.

  • Xiaowei Gao, James Haworth, Dingyi Zhuang, Huanfa Chen, Xinke Jiang, Uncertainty Quantification in Road-level Traffic Risk Prediction by Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network, 12th International Conference on Geographic Information Science (GIScience-2023). (In proceeding)

  • Dingyi Zhuang, Yuzhu Huang, Vindula Jayawardana, Jinhua Zhao, Dajiang Suo, Cathy Wu, The Braess Paradox in Dynamic Traffic, IEEE 25th International Conference on Intelligent Transportation Systems (ITSC 2022). (In proceeding) arXiv description

  • Dingyi Zhuang, Jiangang Jin, Yifan Shen, Wei Jiang, An empirical study on cycle lane network using bike sharing data: the case of Shanghai, 2018 International Conference on Transportation and Space-time Economics. (Oral presentation) PPT

  • Siyu Hao, Dingyi Zhuang, De Zhao, Der-Horng Lee, A Pseudo-3D Convolutional Neural Network based Framework for Short-term Mixed Passenger Flow Prediction in Large-scale Public Transit, Transportation Research Board 2020. (Presentation) PDF