Accurate Traffic Forecasting

Accurate traffic forecasting aims to predict future traffic conditions, enabling efficient urban planning and transportation management. Current research heavily utilizes deep learning, focusing on spatio-temporal graph neural networks (STGNNs) and transformer architectures to capture complex spatial and temporal dependencies in traffic data, often incorporating techniques like attention mechanisms and dynamic graph generation. These advancements improve prediction accuracy, particularly for long-term forecasting and zero-shot generalization across different cities, leading to more effective traffic control and optimized resource allocation. Furthermore, efforts are underway to enhance model interpretability and address challenges posed by irregular or asynchronous data.

Papers

August 16, 2024

OpenCity: Open Spatio-Temporal Foundation Models for Traffic Prediction
Zhonghang Li, Long Xia, Lei Shi, Yong Xu, Dawei Yin, Chao Huang
Traffic Prediction Traffic Forecasting Traffic Datasets Accurate Traffic Forecasting Geospatial Foundation Model

April 18, 2024

DST-GTN: Dynamic Spatio-Temporal Graph Transformer Network for Traffic Forecasting
Songtao Huang, Hongjin Song, Tianqi Jiang, Akbar Telikani, Jun Shen, Qingguo Zhou, Binbin Yong, Qiang Wu
Graph Transformer Traffic Forecasting Traffic Data Accurate Traffic Forecasting

March 25, 2024

LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
Qinyao Luo, Silu He, Xing Han, Yuhan Wang, Haifeng Li
Traffic Data Temporal Transformer Traffic Flow Prediction Traffic Flow Forecasting Accurate Traffic Forecasting Traffic Representation

March 7, 2024

TrafPS: A Shapley-based Visual Analytics Approach to Interpret Traffic
Zezheng Feng, Yifan Jiang, Hongjun Wang, Zipei Fan, Yuxin Ma, Shuang-Hua Yang, Huamin Qu, Xuan Song
State of the Art Deep Traffic Flow Visual Analytics Urban Traffic Accurate Traffic Forecasting Large Scale Spatio Temporal Traffic Understanding

March 5, 2024

TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts
Hyunwook Lee, Sungahn Ko
Spatio Temporal Mixture Component Expert Knowledge Temporal Dependency Temporal Attention Traffic Datasets Traffic Pattern Accurate Traffic Forecasting

August 31, 2023

Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Network
Weijia Zhang, Le Zhang, Jindong Han, Hao Liu, Yanjie Fu, Jingbo Zhou, Yu Mei, Hui Xiong
Traffic Forecasting Accurate Traffic Forecasting Traffic State Sequence

August 14, 2023

ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecasting
Zepu Wang, Yuqi Nie, Peng Sun, Nam H. Nguyen, John Mulvey, H. Vincent Poor
Spatio Temporal Traffic Forecasting Temporal Graph Neural Network Multi Layer Perceptron Accurate Traffic Forecasting

June 15, 2023

Adaptive Hierarchical SpatioTemporal Network for Traffic Forecasting
Yirong Chen, Ziyue Li, Wanli Ouyang, Michael Lepech
Traffic Forecasting Spatiotemporal Modeling Accurate Traffic Forecasting

October 31, 2022

Large scale traffic forecasting with gradient boosting, Traffic4cast 2022 challenge
Martin Lumiste, Andrei Ilie
Challenge Task Traffic Prediction Traffic Forecasting Gradient Boosting Traffic4cast Competition Accurate Traffic Prediction Accurate Traffic Forecasting

September 27, 2022

Explainable Graph Pyramid Autoformer for Long-Term Traffic Forecasting
Weiheng Zhong, Tanwi Mallick, Hadi Meidani, Jane Macfarlane, Prasanna Balaprakash
Accurate Traffic Forecasting Short Term Traffic Long Term Traffic Forecasting

May 18, 2022

Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecasting
Aoyu Liu, Yaying Zhang
Dynamic Graph Temporal Graph Traffic Forecasting Traffic Datasets Accurate Traffic Forecasting

February 25, 2022

Spatio-Temporal Latent Graph Structure Learning for Traffic Forecasting
Jiabin Tang, Tang Qian, Shijing Liu, Shengdong Du, Jie Hu, Tianrui Li
Graph Neural Network Traffic Forecasting Temporal Graph Learning Latent Graph Accurate Traffic Forecasting

February 8, 2022

Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities
Yihong Tang, Ao Qu, Andy H. F. Chow, William H. K. Lam, S. C. Wong, Wei Ma
Urban Environment Task Transferability Traffic Forecasting Internet Service Domain Accurate Traffic Prediction Accurate Traffic Forecasting Short Term Traffic Transferable Time Series Network Wide Traffic

December 6, 2021

Spatio-Temporal meets Wavelet: Disentangled Traffic Flow Forecasting via Efficient Spectral Graph Attention Network
Yuchen Fang, Yanjun Qin, Haiyong Luo, Fang Zhao, Bingbing Xu, Chenxing Wang, Liang Zeng
Traffic Forecasting Wavelet Based Traffic Flow Forecasting Spectral Attention Accurate Traffic Forecasting

November 3, 2021

Multistep traffic speed prediction: A deep learning based approach using latent space mapping considering spatio-temporal dependencies
Shatrughan Modi, Jhilik Bhattacharya, Prasenjit Basak
Latent Space Constructive Approach Temporal Dependency Traffic Prediction Traffic Flow Prediction Traffic Speed Accurate Traffic Prediction Accurate Traffic Forecasting

Accurate Traffic Forecasting

Papers

OpenCity: Open Spatio-Temporal Foundation Models for Traffic Prediction

DST-GTN: Dynamic Spatio-Temporal Graph Transformer Network for Traffic Forecasting

LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting

TrafPS: A Shapley-based Visual Analytics Approach to Interpret Traffic

TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts

Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Network

ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecasting

Adaptive Hierarchical SpatioTemporal Network for Traffic Forecasting

Large scale traffic forecasting with gradient boosting, Traffic4cast 2022 challenge

Explainable Graph Pyramid Autoformer for Long-Term Traffic Forecasting

Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecasting

Spatio-Temporal Latent Graph Structure Learning for Traffic Forecasting

Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities

Spatio-Temporal meets Wavelet: Disentangled Traffic Flow Forecasting via Efficient Spectral Graph Attention Network

Multistep traffic speed prediction: A deep learning based approach using latent space mapping considering spatio-temporal dependencies