Dynamic Interactive Graph Convolutional Recurrent Network for bidirectional spatiotemporal traffic flow forecasting

doi:10.1016/j.engappai.2025.112729

Dynamic Interactive Graph Convolutional Recurrent Network for bidirectional spatiotemporal traffic flow forecasting

2025-10-15

0

PRE

AI

DOI：10.1016/j.engappai.2025.112729

Original

Original request for help

Save

Abstract

En 中文

• A novel traffic inflow and outflow prediction framework, fusing GCN and GRU to capture inflow and outflow spatiotemporal features. • Treating inflows and outflows as both related and independent traffic modes. • An interactive learning gated mechanism, realizing inflow and outflow feature interaction and fusion.

Dynamic Interactive Graph Convolutional Recurrent Network for bidirectional spatiotemporal traffic flow forecasting

Abstract

Journal

Organization