Deep Learning for Short-Term Traffic Flow Prediction

Abstract

We develop a deep learning model to predict traffic flows. The main contribution is development of an architecture that combines a linear model that is fitted using ${\ell }_1$ regularization and a sequence of $\tanh$ layers. The challenge of predicting traffic flows are the sharp nonlinearities due to transitions between free flow, breakdown, recovery and congestion. We show that deep learning architectures can capture these nonlinear spatio-temporal effects. The first layer identifies spatio-temporal relations among predictors and other layers model nonlinear relations. We illustrate our methodology on road sensor data from Interstate I-55 and predict traffic flows during two special events; a Chicago Bears football game and an extreme snowstorm event. Both cases have sharp traffic flow regime changes, occurring very suddenly, and we show how deep learning provides precise short term traffic flow predictions.

References in corpus (10)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Theano: new features and speed improvements
• Fisher Lecture: Dimension Reduction in Regression
• Travel time estimation for ambulances using Bayesian data augmentation
• Fast and Flexible ADMM Algorithms for Trend Filtering
• Prediction, Expectation, and Surprise: Methods, Designs, and Study of a Deployed Traffic Forecasting Service
• Bayesian Particle Tracking of Traffic Flows
• Bayesian analysis of traffic flow on interstate I-55: The LWR model
• Joint Specification of Model Space and Parameter Space Prior Distributions
• On the Inductive Bias of Dropout

Cited by in corpus (48)

• Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach
• Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework
• Flow: A Modular Learning Framework for Mixed Autonomy Traffic
• Applications of deep learning in traffic congestion detection, prediction and alleviation: A survey
• Big Data Analytics for Large Scale Wireless Networks: Challenges and Opportunities
• Deep Learning: A Bayesian Perspective
• A Physics-Informed Deep Learning Paradigm for Traffic State and Fundamental Diagram Estimation
• Macroscopic Traffic Flow Modeling with Physics Regularized Gaussian Process: A New Insight into Machine Learning Applications
• Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting
• Physics-Informed Deep Learning For Traffic State Estimation: A Survey and the Outlook
• Traffic Data Imputation using Deep Convolutional Neural Networks
• Short term prediction of demand for ride hailing services: A deep learning approach
• Semi-Dynamic Load Balancing: Efficient Distributed Learning in Non-Dedicated Environments
• BFRT: Blockchained Federated Learning for Real-time Traffic Flow Prediction
• Heteroscedastic Gaussian processes for uncertainty modeling in large-scale crowdsourced traffic data
• Deep Learning for Spatio-Temporal Data Mining: A Survey
• Comparing hundreds of machine learning classifiers and discrete choice models in predicting travel behavior: an empirical benchmark
• Forecasting: theory and practice
• DeepTransport: Learning Spatial-Temporal Dependency for Traffic Condition Forecasting
• Causal invariant geographic network representations with feature and structural distribution shifts
• ConAML: Constrained Adversarial Machine Learning for Cyber-Physical Systems
• Counterfactual Explanations for Deep Learning-Based Traffic Forecasting
• Dynamic Spatial-Temporal Representation Learning for Traffic Flow Prediction
• Traffic congestion anomaly detection and prediction using deep learning
• From Bytes to Biases: Investigating the Cultural Self-Perception of Large Language Models
• Multistep Speed Prediction on Traffic Networks: A Graph Convolutional Sequence-to-Sequence Learning Approach with Attention Mechanism
• Physics-Informed Deep Learning for Traffic State Estimation
• Learning Traffic Speed Dynamics from Visualizations
• Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks
• Optimizing city-scale traffic through modeling observations of vehicle movements
• A Spatial-Temporal Decomposition Based Deep Neural Network for Time Series Forecasting
• Deep Neural Networks for Choice Analysis: Extracting Complete Economic Information for Interpretation
• Time Series Forecasting with Stacked Long Short-Term Memory Networks
• Short-Term Traffic Flow Prediction Using Variational LSTM Networks
• A Deep Generative Adversarial Architecture for Network-Wide Spatial-Temporal Traffic State Estimation
• Twin-Timescale Radio Resource Management for Ultra-Reliable and Low-Latency Vehicular Networks
• Urban flows prediction from spatial-temporal data using machine learning: A survey
• From Twitter to Traffic Predictor: Next-Day Morning Traffic Prediction Using Social Media Data
• A New Unified Deep Learning Approach with Decomposition-Reconstruction-Ensemble Framework for Time Series Forecasting
• Reconstructing Physics-Informed Machine Learning for Traffic Flow Modeling: a Multi-Gradient Descent and Pareto Learning Approach
• Real time Traffic Flow Parameters Prediction with Basic Safety Messages at Low Penetration of Connected Vehicles
• Short-term Road Traffic Prediction based on Deep Cluster at Large-scale Networks
• Deep Neural Networks for Choice Analysis: Architectural Design with Alternative-Specific Utility Functions
• Optimal charging guidance strategies for electric vehicles by considering dynamic charging requests in a time-varying road network
• Causal Analysis and Prediction of Human Mobility in the U.S. during the COVID-19 Pandemic
• Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice models
• A Graph Convolutional Network with Signal Phasing Information for Arterial Traffic Prediction
• Explainable, automated urban interventions to improve pedestrian and vehicle safety