TITAN: A Spatiotemporal Feature Learning Framework for Traffic Incident Duration Prediction

TL;DR

This paper introduces TITAN, a multi-task learning framework that predicts traffic incident durations and identifies key temporal features using a novel optimization approach, improving accuracy in traffic incident management.

Contribution

The paper presents a new spatiotemporal feature learning model with a specialized optimization algorithm for incident duration prediction and feature identification.

Findings

Outperforms existing models on real-world traffic data

Effectively identifies critical temporal features of traffic incidents

Demonstrates the benefit of incorporating spatial connectivity constraints

Abstract

Critical incident stages identification and reasonable prediction of traffic incident duration are essential in traffic incident management. In this paper, we propose a traffic incident duration prediction model that simultaneously predicts the impact of the traffic incidents and identifies the critical groups of temporal features via a multi-task learning framework. First, we formulate a sparsity optimization problem that extracts low-level temporal features based on traffic speed readings and then generalizes higher level features as phases of traffic incidents. Second, we propose novel constraints on feature similarity exploiting prior knowledge about the spatial connectivity of the road network to predict the incident duration. The proposed problem is challenging to solve due to the orthogonality constraints, non-convexity objective, and non-smoothness penalties. We develop an algorithm based on the alternating direction method of multipliers (ADMM) framework to solve the proposed formulation. Extensive experiments and comparisons to other models on real-world traffic data and traffic incident records justify the efficacy of our model.