📄 中文摘要
交通网络设计是交通领域的重要研究课题，通常通过在固定需求假设下求解优化模型来解决。考虑到这些假设的局限性，提出了一种新的框架，即两级乘客选择交通网络设计（2LRC-TND），该框架利用机器学习和上下文随机优化（CSO）结合约束编程（CP），将两层需求不确定性纳入网络设计过程。第一层识别依赖公共交通的旅客（核心需求），而第二层则基于公共交通服务的可用性和质量，捕捉不依赖公共交通的旅客的条件采纳行为（潜在需求）。
考虑两级需求不确定性的交通网络设计：机器学习与上下文随机优化框架
📄 English Summary
Transit Network Design with Two-Level Demand Uncertainties: A Machine Learning and Contextual Stochastic Optimization Framework
Transit Network Design is a critical area of research in transportation, typically addressed through optimization models under fixed demand assumptions. Recognizing the limitations of these assumptions, a novel framework called Two-Level Rider Choice Transit Network Design (2LRC-TND) is proposed. This framework leverages machine learning and contextual stochastic optimization (CSO) through constraint programming (CP) to incorporate two layers of demand uncertainties into the network design process. The first layer identifies travelers who depend on public transit (core demand), while the second layer captures the conditional adoption behavior of those who do not rely on public transit (latent demand), based on the availability and quality of transit services.