Improved LSTM model for short-term traffic flow prediction with weather consideration

Yuhan Zhou; Jiandong He; Ziyan Wu

doi:10.1117/12.2690126

7 September 2023 Improved LSTM model for short-term traffic flow prediction with weather consideration

Yuhan Zhou, Jiandong He, Ziyan Wu

Proceedings Volume 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023); 1279061 (2023) https://doi.org/10.1117/12.2690126
Event: 8th International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 2023, Hangzhou, China

Abstract

Accurate traffic analysis and prediction are crucial for smart transportation as urban traffic flow is random and influenced by multiple factors. Existing models typically use shallow prediction techniques, resulting in unsatisfactory accuracy when considering external factors such as weather. This study proposes an improved LSTM model with an attention mechanism for short-term traffic flow prediction while considering weather factors. Our model learns the importance of each past value to the current value from past long sequences of traffic data, extracting more valuable features. Our experiments on a PeMS traffic data set show that the proposed model outperforms the original LSTM model, reducing its MAPE by 23.36% and demonstrating its effectiveness in improving traffic flow prediction accuracy.

Citation Download Citation

Yuhan Zhou, Jiandong He, and Ziyan Wu "Improved LSTM model for short-term traffic flow prediction with weather consideration", Proc. SPIE 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 1279061 (7 September 2023); https://doi.org/10.1117/12.2690126

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available