Jun-Hao Lin

An Operationally Interpretable Lag-Aware Directed Spatio-Temporal Graph Neural Network for Real-Time Freeway Traffic Forecasting

Traffic-DiMAGNet is proposed, a lightweight and interpretable lag-aware directed spatio-temporal graph neural network for real-time freeway flow forecasting that outperforms recurrent, diffusion-based, attention-based, and adaptive-graph baselines regarding MAE, RMSE, and MAPE values.