Physics Guided Deep Learning-Based Model for Short-Term Origin-Destination Demand Prediction in Urban Rail Transit Systems Under Pandemic

扫码查看

原文链接

万方数据

外文摘要：Accurate origin-destination(OD)demand prediction is crucial for the efficient operation and manage-ment of urban rail transit(URT)systems,particularly during a pandemic.However,this task faces several limitations,including real-time availability,sparsity,and high-dimensionality issues,and the impact of the pandemic.Consequently,this study proposes a unified framework called the physics-guided adaptive graph spatial-temporal attention network(PAG-STAN)for metro OD demand prediction under pandemic conditions.Specifically,PAG-STAN introduces a real-time OD estimation module to estimate real-time complete OD demand matrices.Subsequently,a novel dynamic OD demand matrix compression module is proposed to generate dense real-time OD demand matrices.Thereafter,PAG-STAN leverages various heterogeneous data to learn the evolutionary trend of future OD ridership during the pandemic.Finally,a masked physics-guided loss function(MPG-loss function)incorporates the physical quantity information between the OD demand and inbound flow into the loss function to enhance model inter-pretability.PAG-STAN demonstrated favorable performance on two real-world metro OD demand data-sets under the pandemic and conventional scenarios,highlighting its robustness and sensitivity for metro OD demand prediction.A series of ablation studies were conducted to verify the indispensability of each module in PAG-STAN.

外文关键词：

Short-term origin-destination demand predictionUrban rail transitPandemicPhysics-guided deep learning

作者：

Shuxin Zhang、Jinlei Zhang、Lixing Yang、Feng Chen、Shukai Li、Ziyou Gao

展开 >

作者单位：

School of Systems Science,Beijing Jiaotong University,Beijing 100044,China

School of Civil Engineering,Beijing Jiao tong University,Beijing 100044,China

基金：

National Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaNational Natural Science Foundation of China

项目编号：

722881017220102972322022

出版年：

2024

DOI：

10.1016/j.eng.2024.04.020

工程(英文)

CSTPCDEI

ISSN：2095-8099

年,卷(期)：2024.41(10)