Accident-Driven Congestion Prediction and Simulation: An Explainable Framework Using Advanced Clustering and Bayesian Networks

TL;DR

This paper presents an explainable framework combining advanced clustering and Bayesian networks to predict and simulate accident-induced traffic congestion, validated through SUMO simulations with high accuracy.

Contribution

It introduces an AutoML-enhanced deep embedding clustering method and a Bayesian network model for accurate, explainable congestion prediction due to accidents.

Findings

AutoML-enhanced DEC outperforms traditional clustering methods.

Bayesian Network achieved 95.6% accuracy in predicting congestion.

SUMO simulations validated the model's reliability in real scenarios.

Abstract

Traffic congestion due to uncertainties, such as accidents, is a significant issue in urban areas, as the ripple effect of accidents causes longer delays, increased emissions, and safety concerns. To address this issue, we propose a robust framework for predicting the impact of accidents on congestion. We implement Automated Machine Learning (AutoML)-enhanced Deep Embedding Clustering (DEC) to assign congestion labels to accident data and predict congestion probability using a Bayesian Network (BN). The Simulation of Urban Mobility (SUMO) simulation is utilized to evaluate the correctness of BN predictions using evidence-based scenarios. Results demonstrate that the AutoML-enhanced DEC has outperformed traditional clustering approaches. The performance of the proposed BN model achieved an overall accuracy of 95.6%, indicating its ability to understand the complex relationship of accidents causing congestion. Validation in SUMO with evidence-based scenarios demonstrated that the BN model's prediction of congestion states closely matches those of SUMO, indicating the high reliability of the proposed BN model in ensuring smooth urban mobility.