PNNs4: a parallel quadruple neural network model for urban intersection turning movement prediction

Accurately predicting the turning traffic flow at urban intersections is crucial for optimizing traffic management strategies and alleviating congestion. Existing traffic flow prediction models often fail to effectively capture the inherent complexity and dynamic variability of intersections, particularly the nonlinear characteristics of turning movements. To address these limitations, this paper proposes a novel parallel quadruple neural networks (PNNs4) model that leverages deep learning and multi-source data feature fusion techniques in a parallel architecture, enabling comprehensive processing of multi-source traffic data. The innovative feature fusion technology enhances the learning capabilities and accuracy in predicting complex traffic patterns. The fusion process involves an innovative combination of spatial and temporal feature extraction, effectively synchronized through element-wise multiplication, enriching the model's input representation and robustness. Experimental validation across 49 intersections in Milton, Ontario, Canada, demonstrates that the PNNs4 model outperforms existing state-of-the-art methods in terms of both accuracy and stability.