Zhanhong Cheng
Postdoctoral Associate at Urban AI Lab, University of Florida, USA
Ph.D. (2022) in Civil Engineering, Postdoc, McGill University, Canada
M.S. (2018) in Transportation Engineering, Harbin Institute of Technology, China
B.Eng. (2016) in Traffic Engineering, Harbin Institute of Technology, China
Research interests
I am interested in understanding, planning, and optimizing urban mobility systems, along with the associated infrastructure and human behavior using expertise in artificial intelligence (AI), machine learning (ML), and transportation engineering. Currently, my research centers three interrelated areas: public transit (e.g., destination and OD matrix inference, travel time and demand forecasting), multimodal travel behavior (e.g., travel patterns in metro, bike-sharing, and E-taxi), and spatiotemporal data modeling (e.g., forecasting and imputation). Through my research, I aim to contribute to creating transportation systems that are more sustainable, efficient, and accessible.
News
- Jan 2025: I attended the 104rd Transportation Research Board Annual Meeting (TRB2025) in Washington D.C., USA. My collaborators and I presented our work in two poster/presentation sessions. Congratulations to Xiaoxu Chen for winning the Best Paper Award from the AED60 TRB Statistical and Econometric Methods Committee!
- Dec 2024: I am glad to give a report on “Modeling Residential Location Choice with Graph Neural Networks” at MIT Urban Mobility Lab. [Slides]
- Nov 2024: I am glad to give a talk on “Travel Behavior for Urban Mobility Prediction” to members of SERMOS Lab and JGT Lab! Thanks for the invitation from Dr. Xiang (Jacob) Yan and Dr. Xilei Zhao.
- August 2024: our paper “Predicting metro incident duration using structured data and unstructured text logs” (authors: Yangyang Zhao, Zhenliang Ma, Hui Peng, and Zhanhong Cheng*) was accepted by Transportmetrica A: Transport Science. [Full-text]
- August 2024: I began my role as a Postdoctoral Associate at the Urban AI Lab, University of Florida.
- July, 2024: I presented “Anomalies in metro passenger demand are predictable – learning causality with ABTransformer” at TransitData 2024, London. [Slides] [Preprint] [Code]
- June, 2024: Our paper “Laplacian convolutional representation for traffic time series imputation” (authors: Xinyu Chen, Zhanhong Cheng, HanQin Cai, Nicolas Saunier, Lijun Sun) was accepted by IEEE Transactions on Knowledge and Data Engineering. [Slides] [Code]
Found more in archived news
Selected publications
- Cheng, Z., Trepanier, M., & Sun, L. (2022). Real-time forecasting of metro origin-destination matrices with high-order weighted dynamic mode decomposition. Transportation science, 56(4), 904-918. [Full-text] [Code] [Slides] (2nd best paper at CASPT and TransitData 2022🏅)
- Chen, X., Cheng, Z., Cai, H., Saunier, N., & Sun, L. (2024). Laplacian convolutional representation for traffic time series imputation. IEEE Transactions on Knowledge and Data Engineering. [Full-text] [Slides] [Code]
- Cheng, Z., Trépanier, M., & Sun, L. (2021). Incorporating travel behavior regularity into passenger flow forecasting. Transportation Research Part C: Emerging Technologies, 128, 103200. [Full-text]
- Cheng, Z., Trépanier, M., & Sun, L. (2021). Probabilistic model for destination inference and travel pattern mining from smart card data. Transportation, 48(4), 2035-2053. [Full-text] [Code]
- Wu, F., Cheng, Z., Chen, H., Qiu, T. Z., & Sun, L. (2024). Traffic state estimation from vehicle trajectories with anisotropic Gaussian processes. Transportation Research Part C: Emerging Technologies, 137, 103687. [Full-text] [Poster] [Code]
- Chen, X., Cheng, Z., Jin, J. G., Trépanier, M., & Sun, L. (2023). Probabilistic forecasting of bus travel time with a Bayesian Gaussian mixture model. Transportation Science, 57(6), 1516-1535. [Full-text] [Slides]