DLW-Net model for traffic flow prediction under adverse weather
- 2 December 2021
- journal article
- research article
- Published by Taylor & Francis in Transportmetrica B: Transport Dynamics
- Vol. 10 (1) , 499-524
Abstract
To predict traffic flow under adverse weather, a hybrid deep learning model concerning adverse weather (DLW-Net) is formulated. The DLW-Net model consists of the target and global analysis parts. For the target analysis part, the spatio-temporal characteristics of traffic flow data are analyzed using the convolutional neural network (CNN), the long short-term memory (LSTM) and gated recurrent unit (GRU) neural networks. For the global analysis part, the variation rules of traffic flow and weather data are extracted using the LSTM model. Additionally, the characteristics of traffic flow under normal and adverse weather are also discussed. The developed model is verified using three cases. The results show that traffic volume and speed would reduce under heavy rain compared to normal weather, however, drizzle has little impact on traffic flow patterns; the rules of traffic speed data are disturbed by strong wind; and the DLW-Net model performs best under all the conditions.Keywords
Funding Information
- Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport (2020B1203)
- National Natural Science Foundation of China (52172314)
- Ministry of Education of China (DUT20JC40)
This publication has 46 references indexed in Scilit:
- Intersection traffic flow forecasting based on ν-GSVR with a new hybrid evolutionary algorithmNeurocomputing, 2015
- Short-term traffic forecasting: Where we are and where we’re goingTransportation Research Part C: Emerging Technologies, 2014
- Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask LearningIEEE Transactions on Intelligent Transportation Systems, 2014
- Short-Term Travel Time Prediction considering the Effects of WeatherTransportation Research Record: Journal of the Transportation Research Board, 2012
- Climate change and human health: present and future risksThe Lancet, 2006
- Optimized and meta-optimized neural networks for short-term traffic flow prediction: A genetic approachTransportation Research Part C: Emerging Technologies, 2005
- Forecasting Traffic Flow Conditions in an Urban Network: Comparison of Multivariate and Univariate ApproachesTransportation Research Record: Journal of the Transportation Research Board, 2003
- Use of Local Linear Regression Model for Short-Term Traffic ForecastingTransportation Research Record: Journal of the Transportation Research Board, 2003
- Long Short-Term MemoryNeural Computation, 1997
- Dynamic prediction of traffic volume through Kalman filtering theoryTransportation Research Part B: Methodological, 1984