mlsanityData to 7 Oct 2026

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction

arXiv 1701.04245 ↗First posted 16 Jan 2017cs.LG stat.MLcited by 67

Not on the map. Why?

Abstract (arXiv)

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 19; 2023: 10; 2024: 10; 2025: 7; 2026: 4.

67 papers.

Sort:

  1. 2021DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Predictioncited by 73
  2. 2021Learning dynamic and hierarchical traffic spatiotemporal features with Transformercited by 26
  3. 2025Harnessing Vision Models for Time Series Analysis: A Surveycited by 26
  4. 2022PGCN: Progressive Graph Convolutional Networks for Spatial-Temporal Traffic Forecastingcited by 13
  5. 2022Data-Driven Traffic Assignment: A Novel Approach for Learning Traffic Flow Patterns Using a Graph Convolutional Neural Networkcited by 12
  6. 2022STGC-GNNs: A GNN-based traffic prediction framework with a spatial-temporal Granger causality graphcited by 12
  7. 2022Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecastingcited by 11
  8. 2022Improving short-term bike sharing demand forecast through an irregular convolutional neural networkcited by 9
  9. 2024Full Bayesian Significance Testing for Neural Networkscited by 8
  10. 2025Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecastingcited by 8
  11. 2025From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?cited by 7
  12. 2021Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Modelscited by 6
38 more
  1. 2021Adversarial Diffusion Attacks on Graph-based Traffic Prediction Modelscited by 5
  2. 2021Predicting Flight Delay with Spatio-Temporal Trajectory Convolutional Network and Airport Situational Awareness Mapcited by 5
  3. 2022A Graph and Attentive Multi-Path Convolutional Network for Traffic Predictioncited by 5
  4. 2023Uncertainty-aware Traffic Prediction under Missing Datacited by 5
  5. 2025Data re-uploading in Quantum Machine Learning for time series: application to traffic forecastingcited by 5
  6. 2021Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) for Short-Term Forecasting of Transit Passenger Flowcited by 4
  7. 2023Semantic-Fused Multi-Granularity Cross-City Traffic Predictioncited by 4
  8. 2024LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecastingcited by 4
  9. 2021Grab the Reins of Crowds: Estimating the Effects of Crowd Movement Guidance Using Causal Inferencecited by 3
  10. 2021CDGNet: A Cross-Time Dynamic Graph-based Deep Learning Model for Traffic Forecastingcited by 3
  11. 2023A Transfer Learning Framework for Proactive Ramp Metering Performance Assessmentcited by 3
  12. 2021MAF-GNN: Multi-adaptive Spatiotemporal-flow Graph Neural Network for Traffic Speed Forecastingcited by 2
  13. 2022Refining time-space traffic diagrams: A simple multiple linear regression modelcited by 2
  14. 2022Traffic-Twitter Transformer: A Nature Language Processing-joined Framework For Network-wide Traffic Forecastingcited by 2
  15. 2022AST-GIN: Attribute-Augmented Spatial-Temporal Graph Informer Network for Electric Vehicle Charging Station Availability Forecastingcited by 2
  16. 2022GT-CausIn: a novel causal-based insight for traffic predictioncited by 2
  17. 2023Graph-Free Learning in Graph-Structured Data: A More Efficient and Accurate Spatiotemporal Learning Perspectivecited by 2
  18. 2023DSTCGCN: Learning Dynamic Spatial-Temporal Cross Dependencies for Traffic Forecastingcited by 2
  19. 2021Traffic Forecasting using Vehicle-to-Vehicle Communicationcited by 1
  20. 2021Multistep traffic speed prediction: A deep learning based approach using latent space mapping considering spatio-temporal dependenciescited by 1
  21. 2021A Comparative Study on Basic Elements of Deep Learning Models for Spatial-Temporal Traffic Forecastingcited by 1
  22. 2022Exploring the impact of spatiotemporal granularity on the demand prediction of dynamic ride-hailingcited by 1
  23. 2022Simpler is better: Multilevel Abstraction with Graph Convolutional Recurrent Neural Network Cells for Traffic Predictioncited by 1
  24. 2022Multi-task Learning for Sparse Traffic Forecastingcited by 1
  25. 2023Adapting to Skew: Imputing Spatiotemporal Urban Data with 3D Partial Convolutions and Biased Maskingcited by 1
  26. 2023Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Modelscited by 1
  27. 2023TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecastingcited by 1
  28. 2024Evaluating the effects of Data Sparsity on the Link-level Bicycling Volume Estimation: A Graph Convolutional Neural Network Approachcited by 1
  29. 2024FRTP: Federating Route Search Records to Enhance Long-term Traffic Predictioncited by 1
  30. 2021Scalable Learning With a Structural Recurrent Neural Network for Short-Term Traffic Predictioncited by 0
  31. 2021Estimating Traffic Speeds using Probe Data: A Deep Neural Network Approachcited by 0
  32. 2021DistTune: Distributed Fine-Grained Adaptive Traffic Speed Prediction for Growing Transportation Networkscited by 0
  33. 2021Traffic Flow Forecasting with Maintenance Downtime via Multi-Channel Attention-Based Spatio-Temporal Graph Convolutional Networkscited by 0
  34. 2021Network-wide Multi-step Traffic Volume Prediction using Graph Convolutional Gated Recurrent Neural Networkcited by 0
  35. 2022STG-GAN: A spatiotemporal graph generative adversarial networks for short-term passenger flow prediction in urban rail transit systemscited by 0
  36. 2022Deep Convolutional Neural Network for Roadway Incident Surveillance Using Audio Datacited by 0
  37. 2022A Transferable Intersection Reconstruction Network for Traffic Speed Predictioncited by 0
  38. 2022Meta-learning Based Short-Term Passenger Flow Prediction for Newly-Operated Urban Rail Transit Stationscited by 0

50 most cited of 67 All 67 (JSON)