GAGNN: a geography-aware graph neural network for citywide commuting flows prediction

• Developed a dual-adjacency attention mechanism integrating geographic and semantic connectivity. • Proposed a Geography-Aware Graph Neural Network (GAGNN) for urban commuting flow prediction. • Established a Comparative Analysis Framework for the Semantic Adjacency Effects of Multi-Source Transportation Networks. • Validated the model on Fuzhou City data, improving MAE, CPC, and prediction accuracy. Urban commuting flow prediction is crucial for optimizing public transportation and improving efficiency, yet traditional models often focus on geographic adjacency, overlooking the complex cross-regional interactions within transportation networks. To address this, we propose a G eography- A ware G raph N eural N etwork (GAGNN) model for commuting flow prediction. The model first jointly encodes the geographic adjacency matrix and semantic adjacency from public transportation networks, developing a comprehensive attention mechanism to fuse regional proximity with cross-regional semantic connectivity. Subsequently, a Graph Attention Network (GAT) is employed to embed the multiple adjacency relations and multi-source geographic knowledge. Finally, graph embeddings are combined with spatial factors into multidimensional feature vectors, fed into an MLP for commuting flow prediction. The model was validated with Fuzhou workday mobile phone data from January to February 2023, assessing the impact of semantic adjacency from different transportation networks on performance. The results show that: (1) We proposed the GAGNN outperforms both traditional models and advanced graph neural network models (e.g., GSGNN), reducing MAE by 14.9% and improving CPC by 2.1%; (2) The type of semantic adjacency significantly impacts model prediction accuracy. Road-based semantic connections perform best, especially for long-distance commuting flows, followed by metro and bus semantic connections, while the absence of semantic connections yields the worst performance. (3) Spatial scale significantly affects model prediction performance. Under road-based semantic adjacency, accuracy slightly declines with increasing scale, whereas metro, bus, and non-semantic connections, prediction accuracy improves. These findings offer effective support for accurate regional commuting flow modeling and public transportation networks optimization.