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 l 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.

• Publication year

  2016

• Venue

  Transportation Research Part C-emerging Technologies

• Publication date

  2016-04-15

• Fields of study

  Mathematics, Computer Science, Engineering

• Identifiers
  DOI 10.1016/j.trc.2017.02.024arXiv 1604.04527
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Points of Significance: Clustering

  2017cited by this paper
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

  2016cited by this paper
• Queue Profile Estimation in Congested Urban Networks with Probe Data

  2015cited by this paper
• Proximal Algorithms in Statistics and Machine Learning

  2015cited by this paper
• Traffic Flow Prediction With Big Data: A Deep Learning Approach

  2015cited by this paper
• Long short-term memory neural network for traffic speed prediction using remote microwave sensor data

  2015cited by this paper
• VARX-L: Structured Regularization for Large Vector Autoregressions with Exogenous Variables

  2015cited by this paper
• Bayesian analysis of traffic flow on interstate I-55: The LWR model

  2014cited by this paper
• Bayesian Particle Tracking of Traffic Flows

  2014cited by this paper
• Dropout: a simple way to prevent neural networks from overfitting

  2014cited by this paper
• On the inductive bias of dropout

  2014influential reference
• Fast and Flexible ADMM Algorithms for Trend Filtering

  2014cited by this paper
• Short-term traffic forecasting: Where we are and where we’re going

  2014cited by this paper
• A Novel Method to Predict Traffic Features Based on Rolling Self-Structured Traffic Patterns

  2014cited by this paper
• Mixtures, envelopes and hierarchical duality

  2014cited by this paper
• Structured Regularization for Large Vector Autoregression

  2014cited by this paper
• Testing and Comparing Neural Network and Statistical Approaches for Predicting Transportation Time Series

  2013cited by this paper
• Dropout Training as Adaptive Regularization

  2013cited by this paper
• Linguistic Regularities in Continuous Space Word Representations

  2013cited by this paper
• Multivariate forecasting of road traffic flows in the presence of heteroscedasticity and measurement errors

  2013influential reference
• Better Word Representations with Recursive Neural Networks for Morphology

  2013cited by this paper
• Regularization and nonlinearities for neural language models: when are they needed?

  2013cited by this paper
• Travel time estimation for ambulances using Bayesian data augmentation

  2013cited by this paper
• Joint Specification of Model Space and Parameter Space Prior Distributions

  2012cited by this paper
• On sequential data assimilation for scalar macroscopic traffic flow models

  2012cited by this paper
• Classification and regression trees

  2012cited by this paper
• Large Scale Distributed Deep Networks

  2012cited by this paper
• Theano: new features and speed improvements

  2012cited by this paper
• Real-time road traffic forecasting using regime-switching space-time models and adaptive LASSO

  2012cited by this paper
• Statistical methods versus neural networks in transportation research: Differences, similarities and some insights

  2011cited by this paper
• Real time queue length estimation for signalized intersections using travel times from mobile sensors

  2011influential reference
• Data augmentation for support vector machines

  2011cited by this paper
• A traffic model for velocity data assimilation

  2010cited by this paper
• The solution path of the generalized lasso

  2010cited by this paper
• Word Representations: A Simple and General Method for Semi-Supervised Learning

  2010cited by this paper
• A NEURAL NETWORK BASED TRAFFIC-FLOW PREDICTION MODEL

  2010cited by this paper
• Characterizing regimes in daily cycles of urban traffic using smooth-transition regressions

  2010cited by this paper
• Optimization for machine learning

  2010cited by this paper
• Melting of Peridotite to 140 Gigapascals

  2010cited by this paper
• An Aggregation Approach to Short-Term Traffic Flow Prediction

  2009cited by this paper
• 1 Trend Filtering

  2009cited by this paper
• Imputation of Ramp Flow Data for Freeway Traffic Simulation

  2009cited by this paper
• Bayesian committee of neural networks to predict travel times with confidence intervals

  2009cited by this paper
• Online Learning Solutions for Freeway Travel Time Prediction

  2008cited by this paper
• Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks

  2008cited by this paper
• An Interior-Point Method for Large-Scale $\ell_1$-Regularized Least Squares

  2007cited by this paper
• Fisher Lecture: Dimension Reduction in Regression

  2007cited by this paper
• Time Series Analysis and Its Applications: With R Examples

  2007cited by this paper
• Weak formulation of boundary conditions for scalar conservation laws: an application to highway traffic modelling

  2006cited by this paper
• POP-TRAFFIC: a novel fuzzy neural approach to road traffic analysis and prediction

  2006cited by this paper
• Short-term freeway traffic flow prediction : Bayesian combined neural network approach

  2006cited by this paper
• A bayesian network approach to traffic flow forecasting

  2006influential reference
• Prediction, Expectation, and Surprise: Methods, Designs, and Study of a Deployed Traffic Forecasting Service

  2005cited by this paper
• Accurate freeway travel time prediction with state-space neural networks under missing data

  2005cited by this paper
• Optimized and meta-optimized neural networks for short-term traffic flow prediction: A genetic approach

  2005cited by this paper
• PRINCETON UNIVERSITY PRESS

  2005cited by this paper
• Travel-time prediction with support vector regression

  2004cited by this paper
• A simple and effective method for predicting travel times on freeways

  2004cited by this paper
• Building Neural Network Models for Time Series: A Statistical Approach

  2002cited by this paper
• Intelligent simulation and prediction of traffic flow dispersion

  2001cited by this paper
• Use of sequential learning for short-term traffic flow forecasting

  2001cited by this paper
• LSTM recurrent networks learn simple context-free and context-sensitive languages

  2001cited by this paper
• TRAFFIC FLOW FORECASTING USING APPROXIMATE NEAREST NEIGHBOR NONPARAMETRIC REGRESSION

  2000cited by this paper
• The Variable Selection Problem

  2000cited by this paper
• Bayesian Inference on Network Traffic Using Link Count Data

  1998cited by this paper
• Long Short-Term Memory

  1997cited by this paper
• TRAFFIC FLOW FORECASTING: COMPARISON OF MODELING APPROACHES

  1997cited by this paper
• Combining kohonen maps with arima time series models to forecast traffic flow

  1996cited by this paper
• Pattern Recognition and Neural Networks

  1995cited by this paper
• Testing for neglected nonlinearity in time series models: A comparison of neural network methods and alternative tests

  1993cited by this paper
• Neural Networks for Pattern Recognition

  1993influential reference
• Nonlinear total variation based noise removal algorithms

  1992cited by this paper
• On Nonlinear Functions of Linear Combinations

  1984cited by this paper
• Distribution of Residual Autocorrelations in Autoregressive-Integrated Moving Average Time Series Models

  1970cited by this paper
• Causal Inference from Observational Data

  1956cited by this paper

• Short-term high-speed rail passenger flow forecasting integrated extended empirical mode decomposition with multivariate and bidirectional support vector machine

  2026cites this paper
• Ownership, regulation, and ESG in transport and logistics: Insights for policy from explainable machine learning

  2026cites this paper
• Current Challenges and Issues in Car Traffic Forecasting

  2026cites this paper
• A data-driven heuristic for the dynamic vehicle routing problem with multiple soft time windows

  2026cites this paper
• Machine learning for intelligent transportation systems

  2026cites this paper
• A transferable framework for cross-city forecasting via invariant structural knowledge learning

  2026cites this paper
• Bayesian Dynamic Gamma Models for Route-Level Travel Time Reliability

  2026cites this paper
• XGBoost–LSTM Regional Traffic Congestion Ratio Prediction Integrating Spatio‐Temporal and Weather Features

  2026cites this paper
• Estimating node importance in transportation networks: A scalable machine learning approach

  2026cites this paper
• Multi-view Spatiotemporal Traffic Prediction Using Evolutionary-Optimized RNN-GCN Networks

  2026cites this paper
• A generative AI–driven intelligent rules framework for traffic accident detection and analysis

  2026cites this paper
• Improving high-frequency demand forecasts for omnichannel grocery retail

  2026cites this paper
• Metro passenger alighting flow prediction for real-time crowding information: A deep learning approach based on sequential images

  2026cites this paper
• Capturing traffic state variation process: An analytical modeling approach

  2025cites this paper
• Comparative Analysis of Neural Network and Machine Learning Models for Short-Term Traffic Flow Prediction on Shenzhen Expressway

  2025cites this paper
• Mode of Transport Prediction Using Deep Learning to Improve QoS in 6G Networks

  2025cites this paper
• Causal invariant geographic network representations with feature and structural distribution shifts

  2025cites this paper
• Independent Mobility GPT (IDM-GPT): A Self-Supervised Multi-Agent Large Language Model Framework for Customized Traffic Mobility Analysis Using Machine Learning Models

  2025cites this paper
• A synchronous spatiotemporal graph neural network for short-term traffic flow prediction

  2025cites this paper
• Probabilistic Deep Learning for Traffic Density Prediction

  2025cites this paper
• A variational mode decomposition assisted temporal-frequency pure convolutional neural network for highway traffic flow forecasting

  2025cites this paper
• Path flow reconstruction under sparse automatic vehicle identification coverage and limited probe vehicle penetration

  2025cites this paper
• Multilevel learning for enhanced traffic congestion prediction using anomaly detection and ensemble learning

  2025cites this paper
• Urban Signalized Intersection Traffic State Prediction: A Spatial–Temporal Graph Model Integrating the Cell Transmission Model and Transformer

  2025cites this paper
• TrafficKAN-GCN: Graph Convolutional-based Kolmogorov-Arnold Network for Traffic Flow Optimization

  2025cites this paper
• Vanishing Stacked-Residual PINN for State Reconstruction of Hyperbolic Systems

  2025cites this paper
• AI-Driven Consensus: Modeling Multi-Agent Networks with Long-Range Interactions through path-Laplacian Matrices

  2025cites this paper
• MM-STFlowNet: A Transportation Hub-Oriented Multi-Mode Passenger Flow Prediction Method via Spatial-Temporal Dynamic Graph Modeling

  2025cites this paper
• An Efficient Decomposition-Driven Linear Framework for Long-Term Time-Series Forecasting

  2025cites this paper
• A Graph Representation Learning Approach for Imbalanced Ship Type Recognition Using AIS Trajectory Data

  2025cites this paper
• Hybrid Mathematical Modeling and Optimization Framework for Branch Flow Estimation at Y-Intersections: A Constraint- Aware Approach with Minimal Sensing Requirements

  2025cites this paper
• F-GGRU: a sensor-driven deep learning framework for smart city weather-aware traffic congestion prediction

  2025cites this paper
• Fidel-TS: A High-Fidelity Multimodal Benchmark for Time Series Forecasting

  2025cites this paper
• A Cloud-Based Spatio-Temporal GNN-Transformer Hybrid Model for Traffic Flow Forecasting with External Feature Integration

  2025cites this paper
• A Systematic Literature Review of Traffic Congestion Forecasting: From Machine Learning Techniques to Large Language Models

  2025cites this paper
• Spatiotemporal graph learning driven by multivariate KAN for urban road network traffic prediction

  2025cites this paper
• Bayesian Double Descent

  2025cites this paper
• A Traffic Flow Prediction Model Based on Vehicle Travel Big Data and Simulation

  2025cites this paper
• Lane level traffic flow prediction in urban networks with missing data — a time accessibility based multi-task learning framework

  2025cites this paper
• Prediction of Dye Removal Using Machine Learning Techniques

  2025cites this paper
• Application of Traffic Load-Balancing Algorithm—Case of Vigo

  2025cites this paper
• Graph neural networks for real-time optimization of autonomous urban transit systems

  2025cites this paper
• Artificial intelligence in disaster management: achievements, challenges, and prospects

  2025cites this paper
• Shall I Merge That Data? Assessing Consistency of Traffic Data Collected from Multiple Sources

  2025cites this paper
• Dynamic Occupancy Rate for Shared Taxi Mobility-on-Demand Services through LSTM and PER-DQN

  2025cites this paper
• Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series Monitoring

  2025cites this paper
• Research on Urban Road Traffic Flow Prediction Based on Sa-Dynamic Graph Convolutional Neural Network

  2025cites this paper
• Traffic congestion predictor: A spatiotemporal graph neural network with congestion-conditional adaptive mechanism and optimization algorithm

  2025cites this paper
• Urban Intersection Traffic Flow Prediction: A Physics-guided Stepwise Framework Utilizing Spatio-Temporal Graph Neural Network Algorithms

  2025cites this paper
• Periodic decomposition and feature enhancement fusion for traffic forecasting

  2025cites this paper
• Research on short-term traffic flow prediction based on the PCC-IGA-LSTM model

  2025cites this paper
• Traffic flow prediction based on improved deep extreme learning machine

  2025cites this paper
• Graph convolutional networks with multi-scale dynamics for traffic speed forecasting

  2025cites this paper
• Research on Traffic Flow Detection by Incorporating Improved Deep Learning Algorithms under Intelligent Transportation Construction

  2025cites this paper
• A Regional Attention Based LSTM Rectifying Method for Accurate and Efficient Traffic Speed Prediction

  2025cites this paper
• Enhancing short-term traffic prediction by integrating trends and fluctuations with attention mechanism

  2025cites this paper
• Empirical study of daily link traffic volume forecasting based on a deep neural network

  2025cites this paper
• Traffic Flow Prediction Using Deep Learning Techniques in Urban Road Networks

  2025cites this paper
• Predicting Accident Severity on Taiwan Highways Using Machine Learning and Electronic Toll Collection (ETC) Data

  2025cites this paper
• Spatiotemporal Parallel Convolutional Network Considering Multidimensional Factors for Short-Term Traffic Flow Prediction

  2025cites this paper
• Traffic Prediction with Data Fusion and Machine Learning

  2025cites this paper
• CASAformer: Congestion-aware sparse attention transformer for traffic speed prediction

  2025cites this paper
• Graph Neural Networks Empowered Origin-Destination Learning for Urban Traffic Prediction

  2025cites this paper
• Potential failures of physics-informed machine learning in traffic flow modeling: theoretical and experimental analysis

  2025cites this paper
• Short-Term Highway Traffic Flow Prediction via Wavelet–Liquid Neural Network Model

  2025cites this paper
• Reconstructing Physics-Informed Machine Learning for Traffic Flow Modeling: a Multi-Gradient Descent and Pareto Learning Approach

  2025cites this paper
• YOLOv8-BCC: Lightweight Object Detection Model Boosts Urban Traffic Safety

  2025cites this paper
• Interpretability Study of Gradient Information in Individual Travel Prediction

  2025cites this paper
• Early detection of risky spatio-temporal congestion in urban traffic

  2025cites this paper
• A Self-Supervised Multi-Agent Large Language Model Framework for Customized Traffic Mobility Analysis Using Machine Learning Models

  2025cites this paper
• Low-high frequency network for spatial-temporal traffic flow forecasting

  2025cites this paper
• Congestion Forecasting Using Machine Learning Techniques: A Systematic Review

  2025cites this paper
• Improved Public Transport OD Matrix Estimation Using an Enhanced Trip Chain Model with Smart Card Data

  2025cites this paper
• Multi-scale time series prediction model based on deep learning and its application

  2025cites this paper
• Artificial intelligence-driven predictive modeling in civil engineering: a comprehensive review

  2025cites this paper
• Short-term traffic flow prediction research based on ICEEMDAN-MPE-PSO-DELM model

  2025cites this paper
• Urban Rail Transit Passenger Flow Prediction with Gaussian Process Regression Based on CEEMDAN

  2025cites this paper
• Enhancing intelligent transportation systems with a more efficient model for long-term traffic predictions based on an attention mechanism and a residual temporal convolutional network

  2025cites this paper
• A study on hybrid-architecture deep learning model for predicting pressure distribution in 2D airfoils

  2025cites this paper
• Time Series Forecasting Using a Hybrid Deep Learning Method: A Bi-LSTM Embedding Denoising Auto Encoder Transformer

  2025cites this paper
• MDHGFN: Multiscale Dual Hypergraph Fusion Spatiotemporal Network for traffic flow prediction

  2025cites this paper
• Enhancing Extreme Learning Machine Robustness via Residual-Variance-Aware Dynamic Weighting and Broyden-Fletcher-Goldfarb-Shanno Optimization: Application to Metro Crowd Flow Prediction

  2025cites this paper
• A review analysis of traffic anomalies detection using data science and deep learning methods

  2025cites this paper
• A comparative study of machine learning models for taxi-demand prediction using a big data framework

  2025cites this paper
• A novel spatio-temporal adaptive network considering time-delay effect for traffic flow forecasting

  2025cites this paper
• OTST: an optimal transport based spatial-temporal graph attention model for traffic flow prediction

  2025cites this paper
• Traffic-Flow Predictor: Predicting Traffic Volume and Patterns

  2025cites this paper
• Economic Feasibility of Drone-Based Traffic Measurement Concept for Urban Environments

  2025cites this paper
• A novel hybrid model for short-term freeway network traffic state prediction under heavy rainstorm

  2025cites this paper
• Optimization of BP neural network traffic flow prediction model based on improved particle swarm algorithm

  2025cites this paper
• Transportation Mode Selection Using Reinforcement Learning in Simulation of Urban Mobility

  2025cites this paper
• Traffic Volume Analysis and Reduction Strategies in Urban Environments

  2025cites this paper
• A comprehensive review of traffic prediction: From traditional machine learning to AutoML

  2025cites this paper
• An optimized hybrid approach for trajectory prediction and vehicle classification at intersections using Dijkstra and random forest enhanced by a genetic algorithm

  2025cites this paper
• Integrating speed reduction index (SRI) and AADT for prioritizing road network mobility improvements: A case study on Thailand’s national highway

  2025cites this paper
• Traffic State Estimation With Spatio-Temporal Autoencoding Transformer (STAT Model)

  2025cites this paper
• Hybrid fuzzy grammar dynamic graph diffusing attention network for traffic flow prediction

  2025cites this paper
• Application Research of Cross-Attention Mechanism for Traffic Prediction Based on Heterogeneous Data

  2025cites this paper
• Prediction of traffic time using XGBoost model with hyperparameter optimization

  2025cites this paper
• AI-Powered Traffic Optimization for Srinagar Smart City

  2025cites this paper