Traffic Forecasting Datasets

Traffic forecasting datasets are crucial for developing and evaluating algorithms that predict future traffic conditions, aiding in urban planning and transportation management. Current research emphasizes creating larger, more realistic datasets that capture the dynamic and complex spatio-temporal patterns of real-world traffic, addressing issues like sensor downtime and evolving infrastructure. This involves the development and application of advanced models, including graph neural networks and transformers, often incorporating techniques like multi-scale learning and online test-time adaptation to improve accuracy and robustness. Improved forecasting accuracy through these datasets and models has significant implications for optimizing traffic flow, reducing congestion, and enhancing the efficiency of transportation systems.

Papers

November 6, 2024

Efficient and Robust Freeway Traffic Speed Estimation under Oblique Grid using Vehicle Trajectory Data
Yang He, Chengchuan An, Yuheng Jia, Jiachao Liu, Zhenbo Lu, Jingxin Xia
High Efficiency Vehicle Trajectory Data Spatiotemporal Traffic Oblique Unmanned Aerial Vehicle Image Traffic Forecasting Datasets

June 18, 2024

XXLTraffic: Expanding and Extremely Long Traffic Dataset for Ultra-Dynamic Forecasting Challenges
Du Yin, Hao Xue, Arian Prabowo, Shuang Ao, Flora Salim
Traffic Forecasting Traffic Datasets Linear Forecasting Traffic Forecasting Datasets

June 17, 2024

SpoT-Mamba: Learning Long-Range Dependency on Spatio-Temporal Graphs with Selective State Spaces
Jinhyeok Choi, Heehyeon Kim, Minhyeong An, Joyce Jiyoung Whang
Temporal Dependency Mamba in Mamba Long Range Dependency Spatio Temporal Graph Selective State Space Traffic Forecasting Datasets

January 8, 2024

Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecasting
Pengxin Guo, Pengrong Jin, Ziyue Li, Lei Bai, Yu Zhang
Traffic Flow Forecasting Temporal Traffic Online Test Time Adaptation Traffic Forecasting Datasets

December 5, 2023

SAMSGL: Series-Aligned Multi-Scale Graph Learning for Spatio-Temporal Forecasting
Xiaobei Zou, Luolin Xiong, Yang Tang, Jürgen Kurths
Graph Signal Spatio Temporal Forecasting Traffic Forecasting Datasets

October 31, 2023

STDA-Meta: A Meta-Learning Framework for Few-Shot Traffic Prediction
Maoxiang Sun, Weilong Ding, Tianpu Zhang, Zijian Liu, Mengda Xing
Traffic Prediction Spatio Temporal Prediction Spatio Temporal Learning Traffic Forecasting Datasets

August 21, 2023

STAEformer: Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting
Hangchen Liu, Zheng Dong, Renhe Jiang, Jiewen Deng, Jinliang Deng, Quanjun Chen, Xuan Song
Spatio Temporal Traffic Forecasting Traffic Flow Forecasting Temporal Traffic Vanilla Transformer Traffic Forecasting Datasets

August 5, 2022

Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting
Juyong Jiang, Binqing Wu, Ling Chen, Kai Zhang, Sunghun Kim
Native Robustness Adversarial Learning Recent Trend Traffic Forecasting Trend Analysis Traffic Forecasting Datasets

Traffic Forecasting Datasets

Papers

Efficient and Robust Freeway Traffic Speed Estimation under Oblique Grid using Vehicle Trajectory Data

XXLTraffic: Expanding and Extremely Long Traffic Dataset for Ultra-Dynamic Forecasting Challenges

SpoT-Mamba: Learning Long-Range Dependency on Spatio-Temporal Graphs with Selective State Spaces

Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecasting

SAMSGL: Series-Aligned Multi-Scale Graph Learning for Spatio-Temporal Forecasting

STDA-Meta: A Meta-Learning Framework for Few-Shot Traffic Prediction

STAEformer: Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting

Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting