Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to content
/ traffic_prediction Public

Traffic prediction is the task of predicting future traffic measurements (e.g. volume, speed, etc.) in a road network (graph), using historical data (timeseries).

License

MIT license
279 stars 46 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

aprbw/traffic_prediction

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

109 Commits
LICENSE
LICENSE
 
 
METRLA_MAE_60.PNG
METRLA_MAE_60.PNG
 
 
PeMSBAY_MAE_60.PNG
PeMSBAY_MAE_60.PNG
 
 
README.md
README.md
 
 
traffic_prediction.bib
traffic_prediction.bib
 
 

Repository files navigation

This list can be considered outdated. For a more up-to-date list, check: https://github.com/lixus7/Time-Series-Works-Conferences

Traffic Prediction

Traffic prediction is the task of predicting future traffic measurements (e.g. volume, speed, etc.) in a road network (graph), using historical data (timeseries).

Things are usually better defined through exclusions, so here are similar things that I do not include:

  • NYC taxi and bike (and other similar datsets, like uber), are not included, because they tend to be represented as a grid, not a graph.

  • Predicting human mobility, either indoors, or through checking-in in Point of Interest (POI), or through a transport network.

  • Predicting trajectory.

  • Predicting the movement of individual cars through sensors for the purpose of self-driving car.

  • Traffic data imputations.

  • Traffic anomaly detections.

The papers are haphazardly selected.

Summary

A tabular summary of paper and publically available datasets. The paper is reverse chronologically sorted. NO GUARANTEE is made that this table is complete or accurate (please raise an issue if you spot any error).

paper venue published date # other datsets METR-LA PeMS-BAY PeMS-D7(M) PeMS-D7(L) PeMS-04 PeMS-08 LOOP SZ-taxi Los-loop PeMS-03 PeMS-07 PeMS-I-405 PeMS-04(S) TOTAL open
TOTAL 38 28 6 3 3 3 3 2 2 1 1 1 1 95
G-SWaN IoTDI 9 May 23 1 1 1 1 4
SCPT ArXiv 9 May 23 1 1 1 1 4
MP-WaveNet ArXiv 9 May 23 1 1 2
GTS ICLR 4 May 21 1 1 1 2
FASTGNN TII 29 Jan 21 1 1
HetGAT JAIHC 23 Jan 21 1 1 2
GST-GAT IEEE Access 6 Jan 21 1 1 2
CLGRN arXiv 4 Jan 21 3 1 1
DKFN SIGSPATIAL 3 Nov 20 1 1 2
STGAM CISP-BMEI 17 Oct 20 1 1 2
ARNN Nat. Commun 11 Sept 20 1 1
ST-TrafficNet ELECGJ 9 Sept 20 1 1 2
M2 J. AdHoc 1 Sept 20 1 1 2
H-STGCN KDD 23 Aug 20 0
SGMN J. TRC 20 Aug 20 1 1 2
GDRNN NTU 16 Aug 20 1 1 2
ISTD-GCN arXiv 10 Aug 20 1 1 2
GTS UCONN 3 Aug 20 1 1 2
FC-GAGA arXiv 30 Jul 20 1 1 2
STGAT IEEE Access 22 Jul 20 1 1 2
STNN T-ITS 16 Jul 20 0
AGCRN arXiv 6 Jul 20 1 1 2
GWNN-LSTM J. Phys. Conf. Ser. 20 Jun 20 1 1
A3T-GCN arXiv 20 Jun 20 1 1 2
TSE-SC Trans-GIS 1 Jun 20 1 1 2
MTGNN arXiv 24 May 20 1 1 2
ST-MetaNet+ TKDE 19 May 20 1 1 2
STGNN WWW 20 Apr 20 1 1 2
STSeq2Seq arXiv 6 Apr 20 1 1 2
DSTGNN arXiv 12 Mar 20 1 1
RSTAG IoT-J 19 Feb 20 1 1 2
GMAN AAAI 7 Feb 20 1 1
MRA-BGCN AAAI 7 Feb 20 1 1 2
STSGCN AAAI 7 Feb 20 1 1 1 1 4
SLCNN AAAI 7 Feb 20 1 1 1 3
DDP-GCN arXiv 7 Feb 20 0
R-SSM ICLR 13 Jan 20 1 1
GWNV2 arXiv 11 Dec 19 1 1 2
DeepGLO NeurIPS 8 Dec 19 1 1 1
STGRAT arXiv 29 Nov 19 1 1 2
TGC-LSTM T-ITS 28 Nov 19 1 1
DCRNN-RIL TrustCom/BigDataSE 31 Oct 19 1 1 2
L-VGAE arXiv 18 Oct 19 1 1
T-GCN T-ITS 22 Aug 19 1 1 2
GWN IJCAI 10 Aug 19 1 1 2
ST-MetaNet KDD 25 Jul 19 1 1
MRes-RGNN-G AAAI 17 Jul 19 1 1 2
CDSA arXiv 23 May 19 1 1
STDGI ICLR 12 Apr 19 1 1
ST-UNet arXiv 13 Mar 19 1 1 1 3
3D-TGCN arXiv 3 Mar 19 1 1 1 3
ASTGCN AAAI 27 Jan 19 1 1 2
PSN T-ITS 17 Aug 18 1 0
GaAN UAI 6 Aug 18 2 1 1
Seq2Seq Hybrid KDD 19 Jul 18 0
STGCN IJCAI 13 Jul 18 1 1 2
DCRNN ICLR 30 Apr 18 1 1 2
SBU-LSTM UrbComp 14 Aug 17 1 1
GRU YAC 5 Jan 17 1 1

Performance

METR-LA MAE@60 mins

PeMS-BAY MAE@60 mins

NOTES: The experimental setttings may vary. But the common setting is:

  • Observation window = 12 timesteps

  • Prediction horizon = 1 timesteps

  • Prediction window = 12 timesteps

  • Metrics = MAE, RMSE, MAPE

  • Train, validation, and test splits = 7/1/2 OR 6/2/2

However, there are many caveats:

  • Some use different models for different prediction horizon.

  • Some use different batch size when testing previous models, as they increase the observation and prediction windows from previous studies, and have difficulties fitting it on GPU using the same batch size.

  • Regarding adjacency matrix, some derive it using Gaussian RBF from the coordinates, some use the actual connectivity, some simply learn it, and some use combinations.

  • Some might also add more context, such as time of day, or day of the week, or weather.

  • DeepGLO in particular, since it is treating it as a multi-channel timeseries without the spatial information, use rolling validation,

  • Many different treatment of missing datasets, from exclusion to imputations.

Dataset

Publically available datasets and where to find them.

Baidu, code: 'umqd'

The following datasets are not publically available:

Also relevant:

Libraries

Paper

The papers are sorted alphabetically based on model name. The citations are based on Google scholar citation.

You can find the bibtex in traffic_prediction.bib (not complete yet)

model citations venue published date paper codes
3D-TGCN 12 arXiv 3 Mar 19 3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting
AGCRN 3 arXiv 6 Jul 20 Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting PyTorch
ARNN 0 Nat. Commun 11 Sep 20 Autoreservoir computing for multistep ahead prediction based on the spatiotemporal information transformation
ASTGCN 63 AAAI 27 Jan 19 Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting Pytorch MXNet
CDSA 2 arXiv 23 May 19 CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputation
CLGRN 0 arXiv 4 Jan 21 Conditional Local Filters with Explainers for Spatio-Temporal Forecasting
DCRNN 427 ICLR 30 Apr 18 DIFFUSION CONVOLUTIONAL RECURRENT NEURAL NETWORK: DATA-DRIVEN TRAFFIC FORECASTING tf PyTorch
DCRNN-RIL 2 TrustCom/BigDataSE 31 Oct 19 Diffusion Convolutional Recurrent Neural Network with Rank Influence Learning for Traffic Forecasting
DDP-GCN 1 arXiv 7 Feb 20 DDP-GCN: Multi-Graph Convolutional Network for Spatiotemporal Traffic Forecasting
DeepGLO 22 NeurIPS 8 Dec 19 Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting
DGCRN 0 ArXiv 30 Apr 21 Spatiotemporal Adaptive Gated Graph Convolution Network for Urban Traffic Flow Forecasting PyTorch
DKFN 0 SIGSPATIAL 3 Nov 20 Graph Convolutional Networks with Kalman Filtering for Traffic Prediction PyTorch
DSTGNN 0 arXiv 12 Mar 20 Dynamic Spatiotemporal Graph Neural Network with Tensor Network
FASTGNN 0 TII 29 Jan 21 FASTGNN: A Topological Information Protected Federated Learning Approach For Traffic Speed Forecasting
FC-GAGA 0 arXiv 30 Jul 20 FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting
FreqST 2 ICDM 17 Nov 21 FreqST: Exploiting Frequency Information in Spatiotemporal Modeling for Traffic Prediction
GaAN 126 UAI 6 Aug 18 GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs MXNet
GDRNN 0 NTU 16 Aug 20 Deep learning approaches for traffic prediction
GMAN 20 AAAI 7 Feb 20 GMAN: A Graph Multi-Attention Network for Traffic Prediction tf
GRU 308 YAC 5 Jan 17 Using LSTM and GRU neural network methods for traffic flow prediction Keras
GST-GAT 0 IEEE Access 6 Jan 21 Modeling Global Spatial–Temporal Graph Attention Network for Traffic Prediction
G-SWaN 0 IoTDI 9 May 23 Because Every Sensor Is Unique, so Is Every Pair: Handling Dynamicity in Traffic Forecasting PyTorch
GTS 0 UCONN 3 Aug 20 End-to-End Structure-Aware Convolutional Networks on Graphs
GTS 0 ICLR 4 May 21 Discrete Graph Structure Learning for Forecasting Multiple Time Series PyTorch
GWN 46 IJCAI 10 Aug 19 Graph WaveNet for Deep Spatial-Temporal Graph Modeling PyTorch
GWNN-LSTM 0 J. Phys. Conf. Ser. 20 Jun 20 Graph Wavelet Long Short-Term Memory Neural Network: A Novel Spatial-Temporal Network for Traffic Prediction.
GWNV2 0 arXiv 11 Dec 19 Incrementally Improving Graph WaveNet Performance on Traffic Prediction PyTorch
H-STGCN 0 KDD 23 Aug 20 Hybrid Spatio-Temporal Graph Convolutional Network: Improving Traffic Prediction with Navigation Data
HetGAT 0 JAIHC 23 Jan 21 HetGAT: a heterogeneous graph attention network for freeway traffic speed prediction
ISTD-GCN 0 arXiv 10 Aug 20 ISTD-GCN: Iterative Spatial-Temporal Diffusion Graph Convolutional Network for Traffic Speed Forecasting
L-VGAE 0 arXiv 18 Oct 19 Decoupling feature propagation from the design of graph auto-encoders
LSTM 39 TENCON 22 Nov 16 Traffic flow prediction with Long Short-Term Memory Networks (LSTMs)
M2 1 J. AdHoc 1 Sep 20 A performance modeling and analysis of a novel vehicular traffic flow prediction system using a hybrid machine learning-based model
MP-WaveNet 0 ArXiv 9 May 23 Message Passing Neural Networks for Traffic Forecasting
MRA-BGCN 7 AAAI 7 Feb 20 Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting
MRes-RGNN-G 20 AAAI 17 Jul 19 Gated Residual Recurrent Graph Neural Networks for Traffic Prediction
MTGNN 7 arXiv 24 May 20 Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
PSN 4 T-ITS 17 Aug 18 Pattern Sensitive Prediction of Traffic Flow Based on Generative Adversarial Framework
R-SSM 0 ICLR 13 Jan 20 Relational State-Space Model for Stochastic Multi-Object Systems
RSTAG 3 IoT-J 19 Feb 20 Reinforced Spatiotemporal Attentive Graph Neural Networks for Traffic Forecasting
SAE 1626 T-ITS 9 Sep 14 Traffic flow prediction with big data: a deep learning approach Keras
SBU-LSTM 157 UrbComp 14 Aug 17 Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction
SCPT 0 ArXiv 9 May 23 Traffic Forecasting on New Roads Unseen in the Training Data Using Spatial Contrastive Pre-Training
Seq2Seq Hybrid 48 KDD 19 Jul 18 Deep Sequence Learning with Auxiliary Information for Traffic Prediction tf
SGMN 1 J. TRC 20 Aug 20 Graph Markov network for traffic forecasting with missing data
SLCNN 1 AAAI 7 Feb 20 Spatio-Temporal Graph Structure Learning for Traffic Forecasting
ST-MetaNet 39 KDD 25 Jul 19 Urban traffic prediction from spatio-temporal data using deep meta learning MXNet
ST-MetaNet+ 0 TKDE 19 May 20 Spatio-Temporal Meta Learning for Urban Traffic Prediction
ST-TrafficNet 2 ELECGJ 9 Sep 20 ST-TrafficNet: A Spatial-Temporal Deep Learning Network for Traffic Forecasting
ST-UNet 11 arXiv 13 Mar 19 ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling
STDGI 3 ICLR 12 Apr 19 Spatio-Temporal Deep Graph Infomax
STGAT 0 IEEE Access 22 Jul 20 STGAT: Spatial-Temporal Graph Attention Networks for Traffic Flow Forecasting
STGAT 0 IEEE Access 22 Jul 20 STGAT: Spatial-Temporal Graph Attention Networks for Traffic Flow Forecasting
STGCN 322 IJCAI 13 Jul 18 Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting tf PyTorch MXNet
STGNN 4 WWW 20 Apr 20 Traffic Flow Prediction via Spatial Temporal Graph Neural Network
STGRAT 6 arXiv 29 Nov 19 STGRAT: A Spatio-Temporal Graph Attention Network for Traffic Forecasting
STNN 0 T-ITS 16 Jul 20 STNN: A Spatio-Temporal Neural Network for Traffic Predictions
STSeq2Seq 0 arXiv 6 Apr 20 Forecast Network-Wide Traffic States for Multiple Steps Ahead: A Deep Learning Approach Considering Dynamic Non-Local Spatial Correlation and Non-Stationary Temporal Dependency
STGAM 1 CISP-BMEI 17 Oct 20 Spatial-Temporal Graph Attention Model on Traffic Forecasting
STSGCN 5 AAAI 7 Feb 20 Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting MXNet
TGC-LSTM 95 T-ITS 28 Nov 19 Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting
TSE-SC 0 Trans-GIS 1 Jun 20 Traffic transformer: Capturing the continuity and periodicity of time series for traffic forecasting
TSSRGCN 4 ICDM 17 Nov 21 TSSRGCN: Temporal Spectral Spatial Retrieval Graph Convolutional Network for Traffic Flow Forecasting
0 arXiv 15 Jul 20 On the Inclusion of Spatial Information for Spatio-Temporal Neural Networks PyTorch
96 NeuCom 27 Nov 18 LSTM-based traffic flow prediction with missing data

Things that would be in the table above if I have more time:

Other works

Other works that is not based on a static-spatial-graph of timeseries:

Other lists:

Acknowledgement

About

Traffic prediction is the task of predicting future traffic measurements (e.g. volume, speed, etc.) in a road network (graph), using historical data (timeseries).

Topics

timeseries time-series neural-network mxnet tensorflow cnn pytorch transformer lstm forecasting attention gcn traffic-prediction time-series-forecasting timeseries-forecasting traffic-flow-prediction traffic-flow-forecasting traffic-forecasting

Resources

Readme

License

MIT license
Activity

Stars

279 stars

Watchers

12 watching

Forks

46 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages