Deep learning models for traffic prediction

This is a summary for deep learning models with open code for traffic prediction.

These models are classified based on the following tasks.

• Traffic flow prediction

• Traffic speed prediction

• On-Demand service prediction

• Travel time prediction

• Traffic accident prediction

• Traffic location prediction

• Others

Task	Model	Paper	Code	Publication
Traffic flow prediction	ST-ResNet	Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction	tf，Pytorch，Keras	AAAI2017/A
	ACFM	ACFM: A Dynamic Spatial-Temporal Network for Traffic Prediction	Pytorch	ACM MM2018/A
	STDN	Revisiting spatial-temporal similarity: A deep learning framework for traffic prediction	Keras	AAAI2019/A
	ASTGCN	Attention based spatial-temporal graph convolutional networks for traffic flow forecasting	Pytorch	AAAI2019/A
	ST-MetaNet	Urban traffic prediction from spatio-temporal data using deep meta learning	MXNet	KDD2019/A
	STSGCN	Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting	MXNet	AAAI2020/A
	STGNN	STGNN: Traffic Flow Prediction via Spatial Temporal Graph Neural Network	Pytorch	WWW2020/A
	AGCRN	Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting	Pytorch	NIPS2020/A
	DSAN	Preserving Dynamic Attention for Long-Term Spatial-Temporal Prediction	tf2	KDD2020/A
	MPGCN	Predicting Origin-Destination Flow via Multi-Perspective Graph Convolutional Network	Pytorch	ICDE2020/A
	ST-GDN	Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network	tf	AAAI2021/A
	TrGNN	Traffic Flow Prediction with Vehicle Trajectories	Pytorch	AAAI2021/A
	STFGNN	Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting	MXNet	AAAI2021/A
	STGODE	STGODE : Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting	Pytorch	KDD2021/A
	ASTGNN	Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting	Pytorch	TKDE2021/A
	STG-NCDE	Graph Neural Controlled Differential Equations for Traffic Forecasting	Pytorch	AAAI2022/A
	STDEN	STDEN Towards Physics-Guided Neural Networks for Traffic Flow Prediction	Pytorch	AAAI2022/A
	SAE	Traffic Flow Prediction With Big Data: A Deep Learning Approach	Keras	TITS2015/B
	STNN	Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery	Pytorch	ICDM2017/B
	ST-3DNet	Deep Spatial–Temporal 3D Convolutional Neural Networks for Traffic Data Forecasting	Keras	TITS2019/B
	STAG-GCN	Spatiotemporal Adaptive Gated Graph Convolution Network for Urban Traffic Flow Forecasting	Pytorch	CIKM2020/B
	ST-CGA	Spatial-Temporal Convolutional Graph Attention Networks for Citywide Traffic Flow Forecasting	Keras	CIKM2020/B
	ResLSTM	Deep Learning Architecture for Short-Term Passenger Flow Forecasting in Urban Rail Transit	Keras	TITS2020/B
	DGCN	Dynamic Graph Convolution Network for Traffic Forecasting Based on Latent Network of Laplace Matrix Estimation	Pytorch	TITS2020/B
	ToGCN	Topological Graph Convolutional Network-Based Urban Traffic Flow and Density Prediction	Pytorch	TITS2020/B
	Multi-STGCnet	Multi-STGCnet: A Graph Convolution Based Spatial-Temporal Framework for Subway Passenger Flow Forecasting	Keras	IJCNN2020/C
	Conv-GCN	Multi-Graph Convolutional Network for Short-Term Passenger Flow Forecasting in Urban Rail Transit	Keras	IET-ITS2020/C
	TCC-LSTM-LSM	A temporal-aware LSTM enhanced by loss-switch mechanism for traffic flow forecasting	Keras	Neurocomputing2021/C
	LSTM/GRU	Using LSTM and GRU neural network methods for traffic flow prediction	Keras	YAC2016/none
	Cluster_LSTM	Foreseeing Congestion using LSTM on Urban Traffic Flow Clusters	Keras	ICSAI2019/none
	CRANN	A Spatio-Temporal Spot-Forecasting Framework forUrban Traffic Prediction	Pytorch	Applied Soft Computing2020/none
	GNN-flow	Learning Mobility Flows from Urban Features with Spatial Interaction Models and Neural Networks	Pytorch	IEEE SMARTCOMP2020/none
	Deep_Sedanion_Network	Traffic flow prediction using Deep Sedenion Networks	Pytorch	arXiv2020
	MATGCN	Multi-Attention Temporal Graph Convolution Network for Traffic Flow Forecasting	Pytorch	本科毕设
Traffic speed prediction	DCRNN	Diffusion convolutional recurrent neural network: Data-driven traffic forecasting	tf，Pytorch	ICLR2018/none
	STGCN	Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting	tf，MXNet，Pytorch，Keras	IJCAI2018/A
	BaiduTraffic	Deep sequence learning with auxiliary information for traffic prediction	tf	KDD2018/A
	Graph WaveNet	Graph wavenet for deep spatial-temporal graph modeling	Pytorch	IJCAI2019/A
	Graph WaveNet-V2	Incrementally Improving Graph WaveNet Performance on Traffic Prediction	Pytorch	arXiv2019/none
	GMAN	Gman: A graph multi-attention network for traffic prediction	tf	AAAI2020/A
	MRA-BGCN	Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting	Pytorch	AAAI2020/A
	MTGNN	Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks	Pytorch	KDD2020/A
	Curb-GAN	Curb-GAN: Conditional Urban Traffic Estimation through Spatio-Temporal Generative Adversarial Networks	Pytorch	KDD2020/A
	AF	Stochastic origin-destination matrix forecasting using dual-stage graph convolutional, recurrent neural networks	tf	ICDE2020/A
	FC-GAGA	FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting	tf	AAAI2021/A
	HGCN	Hierarchical Graph Convolution Networks for Traffic Forecasting	Pytorch	AAAI2021/A
	ST-Norm	ST-Norm: Spatial and Temporal Normalization for Multi-variateTime Series Forecasting	Pytorch	KDD2021/A
	DMSTGCN	Dynamic and Multi-faceted Spatio-temporal Deep Learning for Traffic Speed Forecasting	Pytorch	KDD2021/A
	GTS	Discrete Graph Structure Learning for Forecasting Multiple Time Series	Pytorch	ICLR2021/none
	DKFN	Graph Convolutional Networks with Kalman Filtering for Traffic Prediction	Pytorch	SIGSPATIAL2020/none
	T-GCN	T-gcn: A temporal graph convolutional network for traffic prediction	tf	TITS2019/B
	TGC-LSTM	Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting	Pytorch	TITS2020/B
	ST-GRAT	ST-GRAT: A Novel Spatio-temporal Graph Attention Network for Accurately Forecasting Dynamically Changing Road Speed	Pytorch	CIKM2020/B
	GaAN	GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs	MXNet	UAI2018/B
	TL-DCRNN	Transfer Learning with Graph Neural Networks for Short-Term Highway Traffic Forecasting	tf	ICPR2020/C
	ST-MGAT	ST-MGAT: Spatial-Temporal Multi-Head Graph Attention Networks for Traffic Forecasting	Pytorch	ICTAI2020/C
	DGFN	Dynamic Graph Filters Networks: A Gray-box Model for Multistep Traffic Forecasting	tf2	ITSC2020/none
	ATDM	On the Inclusion of Spatial Information for Spatio-Temporal Neural Networks	Pytorch	arXiv2020/none
	STTN	Spatial-Temporal Transformer Networks for Traffic Flow Forecasting	Pytorch	arXiv2020/none
	DGCRN	Dynamic Graph Convolutional Recurrent Network for Traffic Prediction Benchmark and Solution	Pytorch	arXiv2021/none
	STAWnet	Spatial-temporal attention wavenet: A deep learning framework for traffic prediction considering spatial-temporal dependencies	Pytorch	IET Intelligent Transport Systems2021/C
On-Demand service prediction	DMVST-Net	Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction	Keras	AAAI2018/A
	STG2Seq	Stg2seq: Spatial-temporal graph to sequence model for multi-step passenger demand forecasting	tf	IJCAL2019/A
	GEML	Origin-Destination Matrix Prediction via Graph Convolution: a New Perspective of Passenger Demand Modeling	Keras	KDD2019/A
	CCRNN	Coupled Layer-wise Graph Convolution for Transportation Demand Prediction	Pytorch	AAAI2021/A
	CSTN	Contextualized Spatial–Temporal Network for Taxi Origin-Destination Demand Prediction	Keras	TITS2019/B
	GraphLSTM	Grids versus graphs: Partitioning space for improved taxi demand-supply forecasts	Pytorch	TITS2020/B
	DPFE	Estimating multi-year 24/7 origin-destination demand using high-granular multi-source traffic data	Pytorch	Transportation Research Part C: Emerging Technologies2018/none
	ST-ED-RMGC	Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network	Keras	Transportation Research Part C: Emerging Technologies2021/none
Travel time prediction	DeepTTE	When will you arrive? estimating travel time based on deep neural networks	Pytorch	AAAI2018/A
	HetETA	HetETA: Heterogeneous Information Network Embedding for Estimating Time of Arrival	tf	KDD2020/A
	TTPNet	TTPNet: A Neural Network for Travel Time Prediction Based on Tensor Decomposition and Graph Embedding	Pytorch	TKDE2020/A
	HyperETA	HyperETA: An Estimated Time of Arrival Method based on Hypercube Clustering	Pytorch	techrxiv2021/None
	GSTA	GSTA: gated spatial–temporal attention approach for travel time prediction	tf2	Neural Computing and Applications2021/None
Traffic accident prediction	RiskOracle	RiskOracle: A Minute-Level Citywide Traffic Accident Forecasting Framework	tf	AAAI2020/A
	RiskSeq	Foresee Urban Sparse Traffic Accidents: A Spatiotemporal Multi-Granularity Perspective	tf	TKDE2020/A
	GSNet	GSNet: Learning Spatial-Temporal Correlations from Geographical and Semantic Aspects for Traffic Accident Risk Forecasting	Pytorch	AAAI2021/A
	DSTGCN	Deep Spatio-Temporal Graph Convolutional Network for Traffic Accident Prediction	Pytorch	Neurocomputing2020/C
Traffic location prediction	STRNN	Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts	Pytorch	AAAI2016/A
	DeepMove	DeepMove: Predicting Human Mobility with Attentional Recurrent Networks	Pytorch	WWW2018/A
	HST-LSTM	HST-LSTM: A Hierarchical Spatial-Temporal Long-Short Term Memory Network for Location Prediction	Pytorch	IJCAI2018/A
	VANext	Predciting Human Mobility via Variational Attention	tf	WWW2019/A
	FQA	Multi-agent Trajectory Prediction with Fuzzy Query Attention	Pytorch	NIPS2020/A
	MALMCS	Dynamic Public Resource Allocation based on Human Mobility Prediction	python	UbiComp2020/A
	SERM	SERM: A Recurrent Model for Next Location Prediction in Semantic Trajectories	Keras	CIKM2017/B
Map matching	ST-Matching	Map-matching for low-sampling-rate GPS trajectories	Python	SIGSPATIAL2009/None
	IVMM	An Interactive-Voting Based Map Matching Algorithm	Python	MDM2010/C
	HMMM	Hidden Markov map matching through noise and sparseness	Python	SIGSPATIAL2009/None
	PIF	The Path Inference Filter: Model-Based Low-Latency Map Matching of Probe Vehicle Data	Python	TITS2014/B
Others	seq2seq	Sequence to Sequence Learning with Neural Networks	Keras	NIPS2014/A
	NASR	Empowering A* Search Algorithms with Neural Networks for Personalized Route Recommendation	tf	KDD2019/A
	HRNR	Learning Effective Road Network Representation with Hierarchical Graph Neural Networks	Pytorch	KDD2020/A
	SHARE	Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction	Pytorch	AAAI2020/A
	TALE	Pre-training Time-Aware Location Embeddings from Spatial-Temporal Trajectories	Pytorch	TKDE2021/A
	PVCGN	Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction	Pytorch	TITS2020/B
	DCRNN	Evaluation and prediction of transportation resilience under extreme weather events: A diffusion graph convolutional approach	tf	Transportation Research Part C: Emerging Technologies2020/none
	LibCity	LibCity: An Open Library for Traffic Prediction	Pytorch	SIGSPATIAL2021/None