Explainable Graph Pyramid Autoformer for Long-Term Traffic Forecasting

09/27/2022
by   Weiheng Zhong, et al.
0

Accurate traffic forecasting is vital to an intelligent transportation system. Although many deep learning models have achieved state-of-art performance for short-term traffic forecasting of up to 1 hour, long-term traffic forecasting that spans multiple hours remains a major challenge. Moreover, most of the existing deep learning traffic forecasting models are black box, presenting additional challenges related to explainability and interpretability. We develop Graph Pyramid Autoformer (X-GPA), an explainable attention-based spatial-temporal graph neural network that uses a novel pyramid autocorrelation attention mechanism. It enables learning from long temporal sequences on graphs and improves long-term traffic forecasting accuracy. Our model can achieve up to 35 that of several state-of-the-art methods. The attention-based scores from the X-GPA model provide spatial and temporal explanations based on the traffic dynamics, which change for normal vs. peak-hour traffic and weekday vs. weekend traffic.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/09/2020

Spatial-Temporal Transformer Networks for Traffic Flow Forecasting

Traffic forecasting has emerged as a core component of intelligent trans...
research
10/01/2022

STGIN: A Spatial Temporal Graph-Informer Network for Long Sequence Traffic Speed Forecasting

Accurate long series forecasting of traffic information is critical for ...
research
07/27/2023

HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecasting

Traffic forecasting, which aims to predict traffic conditions based on h...
research
11/15/2021

A Comparative Study on Basic Elements of Deep Learning Models for Spatial-Temporal Traffic Forecasting

Traffic forecasting plays a crucial role in intelligent transportation s...
research
02/08/2022

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

Accurate real-time traffic forecast is critical for intelligent transpor...
research
12/02/2020

Deep Learning for Road Traffic Forecasting: Does it Make a Difference?

Deep Learning methods have been proven to be flexible to model complex p...
research
12/10/2019

Graph Markov Network for Traffic Forecasting with Missing Data

Traffic forecasting is a classical task for traffic management and it pl...

Please sign up or login with your details

Forgot password? Click here to reset