GAGNN: a geography-aware graph neural network for citywide commuting flows prediction
文献类型：期刊论文
| 作者 | Tu, Youjun2,4,5; Wang, Peixiao3; Zhu, Julie N. Y.6; Zhao, Zhiyuan2,4,5; Li, Junli1; Wu, Sheng2,4,5 |
| 刊名 | INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
 |
| 出版日期 | 2026-03-01 |
| 卷号 | 147页码:105175 |
| 关键词 | Commuting flow Transportation networks Geographic adjacency Semantic adjacency Geographic knowledge |
| ISSN号 | 1569-8432 |
| DOI | 10.1016/j.jag.2026.105175 |
| 产权排序 | 3 |
| 文献子类 | Article |
| 英文摘要 | 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 Geography-Aware Graph Neural Network (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. |
| URL标识 | 查看原文 |
| WOS关键词 | MOBILITY |
| WOS研究方向 | Physical Geography ; Remote Sensing |
| 语种 | 英语 |
| WOS记录号 | WOS:001703039500001 |
| 出版者 | ELSEVIER |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/221219]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Zhao, Zhiyuan |
| 作者单位 | 1.Anhui Agr Univ, Coll Resources & Environm, Hefei 230036, Peoples R China 2.Fuzhou Univ, Key Lab Spatial Data Min & Informat Sharing, Minist Educ, Fuzhou 350108, Fujian, Peoples R China; 3.Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China; 4.Acad Digital China, Fuzhou 350003, Fujian, Peoples R China; 5.Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Fujian, Peoples R China; 6.Fuzhou Univ, Coll Econ & Management, Fuzhou 350108, Fujian, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Tu, Youjun,Wang, Peixiao,Zhu, Julie N. Y.,et al. GAGNN: a geography-aware graph neural network for citywide commuting flows prediction[J]. INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION,2026,147:105175. |
| APA | Tu, Youjun,Wang, Peixiao,Zhu, Julie N. Y.,Zhao, Zhiyuan,Li, Junli,&Wu, Sheng.(2026).GAGNN: a geography-aware graph neural network for citywide commuting flows prediction.INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION,147,105175. |
| MLA | Tu, Youjun,et al."GAGNN: a geography-aware graph neural network for citywide commuting flows prediction".INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION 147(2026):105175. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。