Smart City Gnosys

Smart city article details

Title	High-Resolution Urban Flows Forecasting With Coarse-Grained Spatiotemporal Data
ID_Doc	29131
Authors	Xu Z.; Kang Y.; Cao Y.
Year	2023
Published	IEEE Transactions on Artificial Intelligence, 4, 2
DOI	http://dx.doi.org/10.1109/TAI.2022.3153750
Abstract	Urban flow monitoring and forecasting systems play important roles in smart city management. However, due to the long-lasting and enormous deployment cost of ubiquitous traffic monitoring devices (e.g., loop detectors, traffic video detection), it is very difficult to predict flow in high-resolution (HR) with limited monitoring devices. The existing spatiotemporal network based methods usually predict the urban flow in the same spatial scale without considering the spatial correlations between coarse-grained and fine-grained urban flows. To tackle these issues, we propose a HR spatiotemporal transformer network (HRSTT) to predict fine-grained urban flow. Specifically, residual convolution units are employed to constructs the high-level features of three-view temporal (e.g., closeness, period, and trend) flow data. Then, a transformer block is designed to jointly learn the spatiotemporal dynamic features of each temporal flow with self-attention mechanism. For the external factors (e.g., holidays, weather conditions) are extracted by embedding dense networks, which are fused with high level coarse-grained flow feature maps with gated-fusion scheme. Finally, the coarse-grained fusion feature maps are transferred to the distributional upsampling module, generating the fined-grained flow map of target predicted time. Furthermore, the proposed model is evaluated with several baselines on real-world TaxiBJ datasets, demonstrating the state-of-the-art performance of our approach on the fine-grained urban flow forecasting problem. © 2020 IEEE.
Author Keywords	Deep neural network (DNN); high-resolution (HR); urban flow forecasting

Similar Articles

Id	Similarity	Authors	Title	Published
26541	0.912	Liang Y.; Ouyang K.; Sun J.; Wang Y.; Zhang J.; Zheng Y.; Rosenblum D.; Zimmermann R.	Fine-Grained Urban Flow Prediction	The Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021 (2021)
4883	0.904	Cao S.; Wu L.; Wu J.; Wu D.; Li Q.	A Spatio-Temporal Sequence-To-Sequence Network For Traffic Flow Prediction	Information Sciences, 610 (2022)
60279	0.895	Liang Y.; Ouyang K.; Jing L.; Ruan S.; Liu Y.; Zhang J.; Rosenblum D.S.; Zheng Y.	Urbanfm: Inferring Fine-Grained Urban Flows	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2019)
26538	0.894	Ouyang K.; Liang Y.; Liu Y.; Tong Z.; Ruan S.; Zheng Y.; Rosenblum D.S.	Fine-Grained Urban Flow Inference	IEEE Transactions on Knowledge and Data Engineering, 34, 6 (2022)
26540	0.893	Li J.; Wang S.; Zhang J.; Miao H.; Zhang J.; Yu P.S.	Fine-Grained Urban Flow Inference With Incomplete Data	IEEE Transactions on Knowledge and Data Engineering, 35, 6 (2023)
4890	0.889	Zhang Y.; Zhang F.	A Spatiotemporal Neural Network Model For City Traffic Prediction	Proceedings of SPIE - The International Society for Optical Engineering, 12970 (2023)
38040	0.889	Li W.; Chen J.; Zhang Y.; Sun R.; Xia S.; Pan Z.; Luo J.	Msgformer: Revolutionizing Traffic Flow Prediction With Multiscale And Gated Transformer Architecture	IEEE Internet of Things Journal, 12, 2 (2025)
23509	0.887	Ali A.; Ullah I.; Singh S.K.; Sharafian A.; Jiang W.; I. Sherazi H.; Bai X.	Energy-Efficient Resource Allocation For Urban Traffic Flow Prediction In Edge-Cloud Computing	International Journal of Intelligent Systems, 2025, 1 (2025)
38390	0.886	Tian R.; Wang C.; Hu J.; Ma Z.	Multi-Scale Spatial-Temporal Aware Transformer For Traffic Prediction	Information Sciences, 648 (2023)
38047	0.886	Yang S.; Wu Q.; Wang Y.; Zhou Z.	Mstdfgrn: A Multi-View Spatio-Temporal Dynamic Fusion Graph Recurrent Network For Traffic Flow Prediction	Computers and Electrical Engineering, 123 (2025)