The paper introduces the Temporal Graph Convolutional Network (T-GCN), a novel neural network-based approach for traffic forecasting. The T-GCN combines graph convolutional networks (GCNs) and gated recurrent units (GRUs) to capture both spatial and temporal dependencies in traffic data. GCNs are used to learn complex topological structures of the urban road network, while GRUs capture dynamic changes in traffic data over time. The model is evaluated on real-world datasets, demonstrating superior performance compared to state-of-the-art baselines in terms of prediction accuracy and robustness to noise. The T-GCN is shown to be effective for both short-term and long-term traffic forecasting, making it a valuable tool for urban traffic management and planning.The paper introduces the Temporal Graph Convolutional Network (T-GCN), a novel neural network-based approach for traffic forecasting. The T-GCN combines graph convolutional networks (GCNs) and gated recurrent units (GRUs) to capture both spatial and temporal dependencies in traffic data. GCNs are used to learn complex topological structures of the urban road network, while GRUs capture dynamic changes in traffic data over time. The model is evaluated on real-world datasets, demonstrating superior performance compared to state-of-the-art baselines in terms of prediction accuracy and robustness to noise. The T-GCN is shown to be effective for both short-term and long-term traffic forecasting, making it a valuable tool for urban traffic management and planning.