Hierarchical Flow Decomposition for Turning Movement Prediction at Signalized Intersections

TL;DR

This paper introduces HFD-TM, a hierarchical deep learning framework that improves turning movement prediction at signalized intersections by leveraging traffic structure and flow conservation, achieving higher accuracy and efficiency.

Contribution

The study presents a novel hierarchical deep learning approach with a physics-informed loss for better turning movement prediction, significantly reducing training time and improving accuracy.

Findings

HFD-TM reduces MAE by 5.7% over Transformer and 27.0% over GRU.

Hierarchical decomposition yields the largest performance gains.

Training time is 12.8 times lower than DCRNN, suitable for real-time use.

Abstract

Accurate prediction of intersection turning movements is essential for adaptive signal control but remains difficult due to the high volatility of directional flows. This study proposes HFD-TM (Hierarchical Flow-Decomposition for Turning Movement Prediction), a hierarchical deep learning framework that predicts turning movements by first forecasting corridor through-movements and then expanding these predictions to individual turning streams. This design is motivated by empirical traffic structure, where corridor flows account for 65.1% of total volume, exhibit lower volatility than turning movements, and explain 35.5% of turning-movement variance. A physics-informed loss function enforces flow conservation to maintain structural consistency. Evaluated on six months of 15-minute interval LiDAR (Light Detection and Ranging) data from a six-intersection corridor in Nashville, Tennessee, HFD-TM achieves a mean absolute error of 2.49 vehicles per interval, reducing MAE by 5.7% compared to a Transformer and by 27.0% compared to a GRU (Gated Recurrent Unit). Ablation results show that hierarchical decomposition provides the largest performance gain, while training time is 12.8 times lower than DCRNN (Diffusion Convolutional Recurrent Neural Network), demonstrating suitability for real-time traffic applications.