基于深度学习的交通流量预测

如今，随着物联网（Internet of Things）和CPS（Cyber-Physical Systems）技术的快速发展，手机、汽车导航系统和交通传感器都产生了大量的时空数据。通过在这些数据上利用最先进的深度学习技术，城市交通预测已经引起了人工智能和智能交通系统界的广泛关注。这个问题可以用一个三维张量（T，N，C）来统一建模，其中T表示总的时间步骤，N表示空间域的大小（即网状网格或图形节点），C表示信息通道。根据具体的建模策略，最先进的深度学习模型可以分为三类：基于网格、基于图和多变量时间序列模型。在这项研究中，本文首先对深度交通模型以及广泛使用的数据集进行了综合评述，然后建立了一个标准的基准，以相同的设置和指标全面评估它们的性能。本文的基准库名字为DL-Traff，是用两个最流行的深度学习框架实现的，即TensorFlow和PyTorch，这两个框架已经在GitHub上的两个存储库中公开提供，分别为：\url{https://github.com/deepkashiwa20/DL-Traff-Grid}和\url{https://github.com/deepkashiwa20/DL-Traff-Graph}。通过DL-Traff，本文希望为那些对时空数据分析感兴趣的研究人员提供一个有用的资源。在交通预测问题上，道路交通速度和公共地铁系统的客流预测是智能交通系统的核心和关键部分，对交通管理、地铁规划和应急安全措施至关重要。大多数方法选择历史数据中的近期段作为预测未来客流的输入，然而，这将导致地铁客流每天早晚高峰的固有特征信息的丧失。因此，本研究将近期和长期的时间特征汇总，设计了一个堆叠的门控卷积神经网络（GatedCNN），从复杂的历史数据中提取时间特征。另一方面，典型的模型没有考虑不同地铁站之间不同的空间依赖关系。本工作提出了各种相邻关系来表征节点之间的关联程度。为了提取地铁流量中的复杂时空特征，将近期和长期的历史数据合并起来使用门控卷积神经网络（GatedCNN）提取时间特征，通过多图图神经网络（GNN）模块提取多图数据的空间特征。基于此，本文提出了一个在地铁客流预测中对复杂的时空相关性进行联合建模的模型，名为Inter-ST。本文在真实世界数据集上的实验结果表明，本文的Inter-ST模型优于所有先进的方法。

[1] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[2] LECUN Y, BENGIO Y, et al. Convolutional networks for images, speech, and time series[J]. The Handbook of Brain Theory and Neural Networks, 1995, 3361(10): 1995.
[3] LIN Z, FENG J, LU Z, et al. Deepstn+ context-aware spatial-temporal neural network for crowd flow prediction in metropolis[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2019: 1020-1027.
[4] DAI R, XU S, GU Q, et al. Hybrid spatio-temporal graph convolutional network: Improving traffic prediction with navigation data[C]//Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2020: 3074-3082.
[5] ZHENG Y, CAPRA L, WOLFSON O, et al. Urban computing: concepts, methodologies, and applications[J]. ACM Transactions on Intelligent Systems and Technology, 2014, 5(3): 38.
[6] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks [J]. 2017.
[7] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems. 2017: 5998-6008.
[8] ZHANG J, ZHENG Y, QI D. Deep spatio-temporal residual networks for citywide crowd flows prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2017: 1655-1661.
[9] WANG D, CAO W, LI J, et al. Deepsd: supply-demand prediction for online car-hailing services using deep neural networks[C]//IEEE International Conference on Data Engineering. 2017: 243-254.
[10] YAO H, WU F, KE J, et al. Deep multi-view spatial-temporal network for taxi demand prediction [C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2018: 2588-2595.
[11] ZONOOZI A, KIM J J, LI X L, et al. Periodic-crn: A convolutional recurrent model for crowd density prediction with recurring periodic patterns[C]//Proceedings of the International Joint Conference on Artificial Intelligence. 2018: 3732-3738.
[12] YUAN Z, ZHOU X, YANG T. Hetero-convlstm: A deep learning approach to traffic accident prediction on heterogeneous spatio-temporal data[C]//Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018: 984-992.
[13] YAO H, TANG X, WEI H, et al. Revisiting spatial-temporal similarity: a deep learning framework for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2019: 5668-5675.
[14] ZHANG J, ZHENG Y, SUN J, et al. Flow prediction in spatio-temporal networks based on multitask deep learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 32(3): 468-478.
[15] JIANG R, SONG X, HUANG D, et al. Deepurbanevent: A system for predicting citywide crowd dynamics at big events[C]//Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019: 2114-2122.
[16] ZHANG Y, LI Y, ZHOU X, et al. Curb-gan: Conditional urban traffic estimation through spatiotemporal generative adversarial networks[C]//Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2020: 842-852.
[17] YU B, YIN H, ZHU Z. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]//Proceedings of the International Joint Conference on Artificial Intelligence. 2018: 3634-3640.
[18] LI Y, YU R, SHAHABI C, et al. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting[C]//International Conference on Learning Representations. 2018.
[19] CHAI D, WANG L, YANG Q. Bike flow prediction with multi-graph convolutional networks [C]//Proceedings of the ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. 2018: 397-400.
[20] GUO S, LIN Y, FENG N, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence: volume 33. 2019: 922-929.
[21] DIAO Z, WANG X, ZHANG D, et al. Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence: volume 33. 2019: 890-897.
[22] GENG X, LI Y, WANG L, et al. Spatiotemporal multi-graph convolution network for ridehailing demand forecasting[C]//Proceedings of the AAAI conference on artificial intelligence: volume 33. 2019: 3656-3663.
[23] WU Z, PAN S, LONG G, et al. Graph wavenet for deep spatial-temporal graph modeling[C]// Proceedings of the International Joint Conference on Artificial Intelligence. 2019: 1907-1913.
[24] BAI L, YAO L, KANHERE S, et al. Stg2seq: Spatial-temporal graph to sequence model for multi-step passenger demand forecasting[C]//Proceedings of the International Joint Conference on Artificial Intelligence. 2019: 1981-1987.
[25] ZHAO L, SONG Y, ZHANG C, et al. T-gcn: A temporal graph convolutional network for traffic prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(9): 3848-3858.
[26] CUI Z, HENRICKSON K, KE R, et al. Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(11): 4883-4894.
[27] YU J J Q, GU J. Real-time traffic speed estimation with graph convolutional generative autoencoder[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(10).
[28] ZHENG C, FAN X, WANG C, et al. Gman: A graph multi-attention network for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence: volume 34. 2020: 1234-1241.
[29] CHEN W, CHEN L, XIE Y, et al. Multi-range attentive bicomponent graph convolutional network for traffic forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence: volume 34. 2020: 3529-3536.
[30] SONG C, LIN Y, GUO S, et al. Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence: volume 34. 2020: 914-921.
[31] ZHANG Q, CHANG J, MENG G, et al. Spatio-temporal graph structure learning for traffic forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence: volume 34. 2020: 1177-1185.
[32] WANG X, MA Y, WANG Y, et al. Traffic flow prediction via spatial temporal graph neural network[C]//The World Wide Web Conference. 2020: 1082-1092.
[33] BAI L, YAO L, LI C, et al. Adaptive graph convolutional recurrent network for traffic forecasting [C]//Advances in Neural Information Processing Systems: volume 33. 2020: 17804-17815.
[34] LV M, HONG Z, CHEN L, et al. Temporal multi-graph convolutional network for traffic flow prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2020.
[35] GUO K, HU Y, QIAN Z, et al. Dynamic graph convolution network for traffic forecasting based on latent network of laplace matrix estimation[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(2): 1009-1018.
[36] LAI G, CHANG W C, YANG Y, et al. Modeling long-and short-term temporal patterns with deep neural networks[C]//The International ACM SIGIR Conference on Research & Development in Information Retrieval. 2018: 95-104.
[37] ZHANG J, SHI X, XIE J, et al. Gaan: Gated attention networks for learning on large and spatiotemporal graphs[C]//The Conference on Uncertainty in Artificial Intelligence. 2018: 339-349.
[38] LIANG Y, KE S, ZHANG J, et al. Geoman: Multi-level attention networks for geo-sensory time series prediction[C]//Proceedings of the International Joint Conference on Artificial Intelligence. 2018: 3428-3434.
[39] PAN Z, LIANG Y, WANG W, et al. Urban traffic prediction from spatio-temporal data using deep meta learning[C]//Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019: 1720-1730.
[40] SHIH S Y, SUN F K, LEE H Y. Temporal pattern attention for multivariate time series forecasting[J]. Machine Learning, 2019, 108(8-9): 1421-1441.
[41] LI S, JIN X, XUAN Y, et al. Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting[C]//Advances in Neural Information Processing Systems. 2019: 5243-5253.
[42] WU Z, PAN S, LONG G, et al. Connecting the dots: Multivariate time series forecasting with graph neural networks[C]//Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2020: 753-763.
[43] DENG J, CHEN X, JIANG R, et al. St-norm: Spatial and temporal normalization for multivariate time series forecasting[C]//Proceedings of the ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021: 269-278.
[44] SMITH B, DEMETSKY M. Traffic flow forecasting: Comparison of modeling approaches[J]. Journal of Transportation Engineering, 1997, 123(4).
[45] WILLIAMS B M, HOEL L A. Modeling and forecasting vehicular traffic flow as a seasonal arima process: Theoretical basis and empirical results[J]. Journal of Transportation Engineering, 2003, 129(6): 664-672.
[46] ZIVOT E, WANG J. Vector autoregressive models for multivariate time series[J]. Modeling Financial Time Series with S-Plus®, 2006: 385-429.
[47] ZAREMBA W, SUTSKEVER I, VINYALS O. Recurrent neural network regularization[J]. ArXiv Preprint ArXiv:1409.2329, 2014.
[48] CHUNG J, GULCEHRE C, CHO K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[C]//Advances in Neural Information Processing Systems. 2014.
[49] BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[J]. ArXiv Preprint ArXiv:1803.01271, 2018.
[50] LIU Y, ZHENG H, FENG X, et al. Short-term traffic flow prediction with conv-lstm[C]//IEEE International Conference on Wireless Communications and Signal Processing (WCSP). 2017: 1-6.
[51] OORD A V D, DIELEMAN S, ZEN H, et al. Wavenet: A generative model for raw audio[J]. 2016: 125.
[52] ZHOU H, ZHANG S, PENG J, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2021: 11106-11115.
[53] LIU Q, WU S, WANG L, et al. Predicting the next location: A recurrent model with spatial and temporal contexts[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2016: 194-200.
[54] HUANG S, WANG D, WU X, et al. Dsanet: Dual self-attention network for multivariate time series forecasting[C]//Proceedings of the ACM International Conference on Information & Knowledge Management. 2019: 2129-2132.
[55] CHENG J, HUANG K, ZHENG Z. Towards better forecasting by fusing near and distant future visions[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020: 3593-3600.
[56] LI Z, HE J, LIU H, et al. Combining global and sequential patterns for multivariate time series forecasting[C]//IEEE International Conference on Big Data. 2020: 180-187.
[57] CHEN P, LIU R, AIHARA K, et al. Autoreservoir computing for multistep ahead prediction based on the spatiotemporal information transformation[J]. Nature Communications, 2020, 11 (1): 1-15.
[58] LIM B, ARIK S Ö, LOEFF N, et al. Temporal fusion transformers for interpretable multihorizon time series forecasting[J]. International Journal of Forecasting, 2021, 37(4): 1748-1764.
[59] ORESHKIN B N, CARPOV D, CHAPADOS N, et al. N-BEATS: neural basis expansion analysis for interpretable time series forecasting[C]//International Conference on Learning Representations. 2020.
[60] ORESHKIN B N, AMINI A, COYLE L, et al. Fc-gaga: Fully connected gated graph architecture for spatio-temporal traffic forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2021: 9233-9241.
[61] FARNOOSH A, AZARI B, OSTADABBAS S. Deep switching auto-regressive factorization: Application to time series forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2021: 7394-7403.
[62] HE H, ZHANG Q, BAI S, et al. Catn: Cross attentive tree-aware network for multivariate time series forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2022.
[63] CHEN E, YE Z, WANG C, et al. Subway passenger flow prediction for special events using smart card data[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(3): 1109-1120.
[64] HAO S, LEE D H, ZHAO D. Sequence to sequence learning with attention mechanism for short-term passenger flow prediction in large-scale metro system[J]. Transportation Research Part C: Emerging Technologies, 2019, 107: 287-300.
[65] CHEN C, LI K, TEO S G, et al. Gated residual recurrent graph neural networks for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2019: 485-492.
[66] HE Z, CHOW C Y, ZHANG J D. Stnn: A spatio-temporal neural network for traffic predictions [J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(12): 7642-7651.
[67] CUI Z, LIN L, PU Z, et al. Graph markov network for traffic forecasting with missing data[J]. Transportation Research Part C: Emerging Technologies, 2020, 117: 102671.
[68] LU Y J, LI C T. Agstn: Learning attention-adjusted graph spatio-temporal networks for shortterm urban sensor value forecasting[C]//IEEE International Conference on Data Mining. 2020: 1148-1153.
[69] HUANG R, HUANG C, LIU Y, et al. Lsgcn: Long short-term traffic prediction with graph convolutional networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020: 2355-2361.
[70] SHANG C, CHEN J, BI J. Discrete graph structure learning for forecasting multiple time series [C]//International Conference on Learning Representations. 2021.
[71] PARK C, LEE C, BAHNG H, et al. St-grat: A novel spatio-temporal graph attention networks for accurately forecasting dynamically changing road speed[C]//Proceedings of the ACM International Conference on Information & Knowledge Management. 2020: 1215-1224.
[72] ZHANG X, HUANG C, XU Y, et al. Spatial-temporal convolutional graph attention networks for citywide traffic flow forecasting[C]//Proceedings of the ACM International Conference on Information & Knowledge Management. 2020: 1853-1862.
[73] LU B, GAN X, JIN H, et al. Spatiotemporal adaptive gated graph convolution network for urban traffic flow forecasting[C]//Proceedings of the ACM International Conference on Information & Knowledge Management. 2020: 1025-1034.
[74] ZHANG X, HUANG C, XU Y, et al. Traffic flow forecasting with spatial-temporal graph diffusion network[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2021: 15008-15015.
[75] CHEN Y, SEGOVIA-DOMINGUEZ I, GEL Y R. Z-gcnets: Time zigzags at graph convolutional networks for time series forecasting[C]//Proceedings of the International Conference on Machine Learning: volume 139. PMLR, 2021: 1684-1694.
[76] FANG Z, LONG Q, SONG G, et al. Spatial-temporal graph ode networks for traffic flow forecasting[C]//Proceedings of the ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021: 364-373.
[77] ZHANG C, ZHANG S, YU J J Q, et al. Fastgnn: A topological information protected federated learning approach for traffic speed forecasting[J]. IEEE Transactions on Industrial Informatics, 2021, 17(12): 8464-8474.
[78] YE J, ZHAO J, YE K, et al. Multi-stgcnet: A graph convolution based spatial-temporal framework for subway passenger flow forecasting[C]//IEEE International Joint Conference on Neural Networks. 2020: 1-8.
[79] Deep learning architecture for short-term passenger flow forecasting in urban rail transit[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, PP(99): 1-11.
[80] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016: 770-778.
[81] ZHOU Q, GU J, LU X, et al. Modeling heterogeneous relations across multiple modes for potential crowd flow prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2021: 4723-4731.
[82] WANG J, ZHANG Y, WEI Y, et al. Metro passenger flow prediction via dynamic hypergraph convolution networks[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22 (12): 7891-7903.
[83] ZHANG J, CHEN F, GUO Y, et al. Multi-graph convolutional network for short-term passenger flow forecasting in urban rail transit[J]. IET Intelligent Transport Systems, 2020, 14(10): 1210-1217.
[84] YE J, SUN L, DU B, et al. Coupled layer-wise graph convolution for transportation demand prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2021: 4617-4625.
[85] OU J, SUN J, ZHU Y, et al. Stp-trellisnets: Spatial-temporal parallel trellisnets for metro station passenger flow prediction[C]//Proceedings of the ACM International Conference on Information & Knowledge Management. 2020: 1185-1194.
[86] PENG H, WANG H, DU B, et al. Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting[J]. Information Sciences, 2020, 521: 277-290.
[87] WANG Y, LONG M, WANG J, et al. Predrnn: Recurrent neural networks for predictive learning using spatiotemporal lstms[C]//Advances in Neural Information Processing Systems. 2017: 879-888.
[88] MA X, DAI Z, HE Z, et al. Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction[J]. Sensors, 2017, 17(4): 818.
[89] VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks[C]// International Conference on Learning Representations. 2018.
[90] HOANG M X, ZHENG Y, SINGH A K. Forecasting citywide crowd flows based on big data[J]. Proceedings of the ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 2016.
[91] ZHANG J, ZHENG Y, QI D, et al. Dnn-based prediction model for spatio-temporal data[C]// Proceedings of the ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. 2016: 92.
[92] YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[C]//International Conference on Learning Representations. 2016.
[93] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[94] DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[C]//Advances in Neural Information Processing Systems. 2016: 3844-3852.
[95] XINGJIAN S, CHEN Z, WANG H, et al. Convolutional lstm network: A machine learning approach for precipitation nowcasting[C]//Advances in Neural Information Processing Systems. 2015: 802-810.
[96] CHOLLET F. keras[EB/OL]. 2015. https://github.com/fchollet/keras.
[97] ABADI M, AGARWAL A, BARHAM P, et al. TensorFlow: Large-scale machine learning on heterogeneous systems[EB/OL]. 2015. http://tensorflow.org/.
[98] PASZKE A, GROSS S, MASSA F, et al. Pytorch: An imperative style, high-performance deep learning library[M]//WALLACH H, LAROCHELLE H, BEYGELZIMER A, et al. Advances in Neural Information Processing Systems. 2019: 8024-8035.
[99] DAUPHIN Y N, FAN A, AULI M, et al. Language modeling with gated convolutional networks [C]//Proceedings of the International Conference on Machine Learning. 2017: 933-941.
[100] SHANG S, CHEN L, WEI Z, et al. Trajectory similarity join in spatial networks[J]. Proceedings of the VLDB Endowment, 2017, 10(11): 1178-1189.