主讲人： 刘芷辰博士，石溪大学土木工程系，助理教授

讲座时间：2025年12月23日11：00

讲座地点：同济大厦A楼402教室

报告摘要：

预计到 2035年，新出厂的车辆中将有近一半实现互联，这将产生前所未有的海量出行数据。交通网络均衡模型已作为交通系统规划和管理基础长达七十多年， 本次报告将利用这些新兴的网联汽车数据，构建一个 AI驱动的逆向学习框架从海量出行数据中自动建立交通网络均衡模型。

传统的交通网络均衡模型在校准时通常费时且成本高昂。本报告提出基于 AI驱动的逆向学习作为一个全新框架直接从海量出行数据中构建出 非参数化、适应环境的交通网络均衡模型。其中，在数据充分的条件下，基于神经网络的非参数化逆向学习框架无需预设任何行为假设，能够自动从海量数据中直接学习任何适定的网络均衡模型。相对而言，半参数化逆向学习框架则通过将逆向学习问题简化为一系列 凸优化 过程，展现出更强的计算可行性。 我们将从数学角度对比非参数化与参数化方法，理论分析构建网络均衡模型时在行为真实性、数据供给和计算成本 之间的取舍。

最后，我们将逆向学习框架应用于密歇根州安娜堡市的长期网络设计问题。通过利用真实世界的车辆轨迹数据学习一个适应环境的交通网络均衡模型，并引入了一种自动微分加速算法，来解决在情境不确定性下所产生的 分布鲁棒双层网络设计问题。

报告人介绍：

刘芷辰博士，目前担任石溪大学土木工程系助理教授。她的研究聚焦于 互联、电动化和自动化背景下，为交通和物流系统开发新一代建模与计算工具。她拥有密歇根大学土木工程博士学位和工业与运筹工程硕士学位，并曾任通用汽车公司的访问科学家。

Zhichen Liu, Ph.D

Assistant Professor, Department of Civil Engineering,

Stony Brook University

Title: Inverse Learning and Intervention of Transportation Network Equilibrium

Abstract:

By 2035, nearly half of all new vehicles will be connected, generating unprecedented volumes of mobility data. Leveraging emerging connected mobility data, this talk establishes an AI-enabled inverse learning framework to transform the transportation network equilibrium modeling paradigm, which has been the foundation of system planning and management for over seventy years.

Traditional transportation network equilibrium models are time-consuming and costly to calibrate. This talk presents the inverse learning of user equilibrium as a novel framework for constructing nonparametric, context-dependent network equilibrium models directly from empirical travel patterns. We compare nonparametric and parametric approaches, mathematically clarifying the trade-offs among behavioral realism, data availability, and computational cost. The proposed neural-network-based nonparametric framework can automatically discover any well-posed network equilibrium model given sufficient data, without relying on predefined behavioral assumptions. In contrast, the semi-parametric approach is more computationally tractable, as it simplifies the inverse learning problem into a sequence of convex optimizations.

Finally, we apply the inverse learning framework to a long-term network design problem for the city of Ann Arbor, Michigan. Using real-world crowdsourced data, we learned a context-dependent equilibrium model and introduce a certified, auto-differentiation-accelerated algorithm to solve the resulting distributionally robust bi-level network design problem under contextual uncertainty.

Short Bio:

Dr. Zhichen Liu is an Assistant Professor in the Stony Brook University Department of Civil Engineering. Her research focuses on innovating next-generation modeling and computational tools for mobility and logistics systems, with an emphasis on connectivity, electrification, and automation. She received her Ph.D. in Civil Engineering and M.S. in Industrial and Operational Engineering from the University of Michigan, and previously served as a Visiting Scientist at General Motors.