Incident duration prediction using a bi-level machine learning framework with outlier removal and intra-extra joint optimisation

TL;DR

This paper introduces a bi-level machine learning framework with outlier removal and joint optimisation to accurately predict traffic incident durations, classifying incidents as short or long-term and providing minute-level predictions across diverse datasets.

Contribution

The paper proposes a novel bi-level ML framework with outlier removal and intra-extra joint optimisation for incident duration prediction, including a new threshold and classification approach.

Findings

Optimal split threshold of 40-45 minutes for incident classification

IEO-ML significantly outperforms baseline models in 66% of cases

Time, location, incident type, and weather are key factors influencing incident duration

Abstract

Predicting the duration of traffic incidents is a challenging task due to the stochastic nature of events. The ability to accurately predict how long accidents will last can provide significant benefits to both end-users in their route choice and traffic operation managers in handling of non-recurrent traffic congestion. This paper presents a novel bi-level machine learning framework enhanced with outlier removal and intra-extra joint optimisation for predicting the incident duration on three heterogeneous data sets collected for both arterial roads and motorways from Sydney, Australia and San-Francisco, U.S.A. Firstly, we use incident data logs to develop a binary classification prediction approach, which allows us to classify traffic incidents as short-term or long-term. We find the optimal threshold between short-term versus long-term traffic incident duration, targeting both class balance and prediction performance while also comparing the binary versus multi-class classification approaches. Secondly, for more granularity of the incident duration prediction to the minute level, we propose a new Intra-Extra Joint Optimisation algorithm (IEO-ML) which extends multiple baseline ML models tested against several regression scenarios across the data sets. Final results indicate that: a) 40-45 min is the best split threshold for identifying short versus long-term incidents and that these incidents should be modelled separately, b) our proposed IEO-ML approach significantly outperforms baseline ML models in $66\%$ of all cases showcasing its great potential for accurate incident duration prediction. Lastly, we evaluate the feature importance and show that time, location, incident type, incident reporting source and weather at among the top 10 critical factors which influence how long incidents will last.