Predicting Subway Passenger Flows under Incident Situation with Causality
#subway passenger flow prediction #incident response #causal inference #synthetic control method #transportation management #machine learning applications #public transit safety #data scarcity challenges
📌 Key Takeaways
- Researchers developed a two-stage method to predict subway passenger flows during incidents
- The approach separates normal condition predictions from incident causal effects
- Method uses synthetic control and placebo tests to identify significant incident effects
- Research improves accuracy and provides interpretability for subway operators
📖 Full Retelling
Researchers Xiannan Huang, Shuhan Qiu, Quan Yuan, and Chao Yang have developed a novel two-stage method for predicting subway passenger flows during incidents in their paper published on arXiv on February 24, 2026, addressing the critical gap in transportation research where most models focus only on normal conditions with limited ability to handle emergency situations. Their approach tackles intrinsic challenges in incident prediction such as lack of interpretability and data scarcity by separating predictions into normal conditions and the causal effects of incidents. The methodology begins with training a normal prediction model using data from standard operating conditions, then employs the synthetic control method to identify the causal effects of incidents, combined with placebo tests to determine the significance of these effects. During the prediction phase, the results from both models are integrated to generate final passenger flow predictions during incidents. This approach has been validated using real-world data, demonstrating improved accuracy in predicting passenger flows during emergency situations.
🏷️ Themes
Machine Learning, Transportation Systems, Causal Inference, Public Safety
Entity Intersection Graph
No entity connections available yet for this article.
Original Source
--> Computer Science > Machine Learning arXiv:2412.06871 [Submitted on 9 Dec 2024 ( v1 ), last revised 24 Feb 2026 (this version, v2)] Title: Predicting Subway Passenger Flows under Incident Situation with Causality Authors: Xiannan Huang , Shuhan Qiu , Quan Yuan , Chao Yang View a PDF of the paper titled Predicting Subway Passenger Flows under Incident Situation with Causality, by Xiannan Huang and 3 other authors View PDF HTML Abstract: In the context of rail transit operations, real-time passenger flow prediction is essential; however, most models primarily focus on normal conditions, with limited research addressing incident situations. There are several intrinsic challenges associated with prediction during incidents, such as a lack of interpretability and data scarcity. To address these challenges, we propose a two-stage method that separates predictions under normal conditions and the causal effects of incidents. First, a normal prediction model is trained using data from normal situations. Next, the synthetic control method is employed to identify the causal effects of incidents, combined with placebo tests to determine significant levels of these effects. The significant effects are then utilized to train a causal effect prediction model, which can forecast the impact of incidents based on features of the incidents and passenger flows. During the prediction phase, the results from both the normal situation model and the causal effect prediction model are integrated to generate final passenger flow predictions during incidents. Our approach is validated using real-world data, demonstrating improved accuracy. Furthermore, the two-stage methodology enhances interpretability. By analyzing the causal effect prediction model, we can identify key influencing factors related to the effects of incidents and gain insights into their underlying mechanisms. Our work can assist subway system managers in estimating passenger flow affected by incidents and enable them to ...
Read full article at source