mlsanityData to 7 Oct 2026

Short-term traffic prediction using physics-aware neural networks

arXiv 2109.10253 ↗First posted 21 Sep 2021cs.LG eess.SPcited by 6

Not on the map. Why?

Abstract (arXiv)

In this work, we propose an algorithm performing short-term predictions of the flux of vehicles on a stretch of road, using past measurements of the flux. This algorithm is based on a physics-aware recurrent neural network. A discretization of a macroscopic traffic flow model (using the so-called Traffic Reaction Model) is embedded in the architecture of the network and yields flux predictions based on estimated and predicted space-time dependent traffic parameters. These parameters are themselves obtained using a succession of LSTM ans simple recurrent neural networks. Besides, on top of the predictions, the algorithm yields a smoothing of its inputs which is also physically-constrained by the macroscopic traffic flow model. The algorithm is tested on raw flux measurements obtained from loop detectors.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 16 of its 47 references that are in the map. First posted on arXiv 21 Sep 2021.

Builds on

16 of 47 references.

References · 16

  1. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  2. 2018Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Networkcited by 415
  3. 2017PDE-Net: Learning PDEs from Datacited by 304
  4. 2018PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Networkcited by 208
  5. 2018Deep Neural Networks Motivated by Partial Differential Equationscited by 187
  6. 2015Visualizing and Understanding Recurrent Networkscited by 158
  7. 2021A Physics-Informed Deep Learning Paradigm for Traffic State and Fundamental Diagram Estimationcited by 37
  8. 2020Solving inverse-PDE problems with physics-aware neural networkscited by 27
  9. 2020Macroscopic Traffic Flow Modeling with Physics Regularized Gaussian Process: A New Insight into Machine Learning Applicationscited by 25
  10. 2019Data driven approximation of parametrized PDEs by Reduced Basis and Neural Networkscited by 21
  11. 2017Neural network augmented inverse problems for PDEscited by 11
  12. 2020Learning-based Traffic State Reconstruction using Probe Vehiclescited by 10
4 more
  1. 2020Deep Learning on Traffic Prediction: Methods, Analysis and Future Directionscited by 8
  2. 2020Short-term Traffic Prediction with Deep Neural Networks: A Surveycited by 8
  3. 2021Parameter and density estimation from real-world traffic data: A kinetic compartmental approachcited by 2
  4. 2021The Traffic Reaction Model: A kinetic compartmental approach to road traffic modelingcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 0; 2025: 3.

6 papers.

  1. 2023Fourier neural operator for learning solutions to macroscopic traffic flow models: Application to the forward and inverse problemscited by 12
  2. 2023A Physics Enhanced Residual Learning (PERL) Framework for Vehicle Trajectory Predictioncited by 5
  3. 2025Potential failures of physics-informed machine learning in traffic flow modeling: theoretical and experimental analysiscited by 1
  4. 2023Controlled Descent Trainingcited by 0
  5. 2025Reconstructing Physics-Informed Machine Learning for Traffic Flow Modeling: a Multi-Gradient Descent and Pareto Learning Approachcited by 0
  6. 2025Proxy Reconstruction Pre-training for Ramp Flow Prediction at Highway Interchangescited by 0