mlsanityData to 7 Oct 2026

Urban traffic analysis and forecasting through shared Koopman eigenmodes

arXiv 2409.04728 ↗First posted 7 Sep 2024eess.SY cs.LG cs.SYcited by 3

Not on the map. Why?

Abstract (arXiv)

Predicting traffic flow in data-scarce cities is challenging due to limited historical data. To address this, we leverage transfer learning by identifying periodic patterns common to data-rich cities using a customized variant of Dynamic Mode Decomposition (DMD): constrained Hankelized DMD (TrHDMD). This method uncovers common eigenmodes (urban heartbeats) in traffic patterns and transfers them to data-scarce cities, significantly enhancing prediction performance. TrHDMD reduces the need for extensive training datasets by utilizing prior knowledge from other cities. By applying Koopman operator theory to multi-city loop detector data, we identify stable, interpretable, and time-invariant traffic modes. Injecting ``urban heartbeats'' into forecasting tasks improves prediction accuracy and has the potential to enhance traffic management strategies for cities with varying data infrastructures. Our work introduces cross-city knowledge transfer via shared Koopman eigenmodes, offering actionable insights and reliable forecasts for data-scarce urban environments.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 19 of its 143 references that are in the map. First posted on arXiv 7 Sep 2024.

Builds on

19 of 143 references.

References · 19

  1. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
  2. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
  3. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 491
  4. 2023ForecastPFN: Synthetically-Trained Zero-Shot Forecastingcited by 102
  5. 2024Language Models Still Struggle to Zero-shot Reason about Time Seriescited by 81
  6. 2020Meta-learning framework with applications to zero-shot time-series forecastingcited by 70
  7. 2019Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Predictioncited by 64
  8. 2023Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bankcited by 22
  9. 2021Incorporating Kinematic Wave Theory into a Deep Learning Method for High-Resolution Traffic Speed Estimationcited by 12
  10. 2023Fourier neural operator for learning solutions to macroscopic traffic flow models: Application to the forward and inverse problemscited by 12
  11. 2020Nonlinear Traffic Prediction as a Matrix Completion Problem with Ensemble Learningcited by 10
  12. 2022Discovering Dynamic Patterns from Spatiotemporal Data with Time-Varying Low-Rank Autoregressioncited by 6
7 more
  1. 2023Learning-based solutions to nonlinear hyperbolic PDEs: Empirical insights on generalization errorscited by 6
  2. 2023Traffic Prediction with Transfer Learning: A Mutual Information-based Approachcited by 6
  3. 2016Multi-scale Perimeter Control Approach in a Connected-Vehicle Environmentcited by 5
  4. 2018Traffic state estimation using stochastic Lagrangian dynamicscited by 5
  5. 2021Learning Traffic Speed Dynamics from Visualizationscited by 4
  6. 2023Generalized adaptive smoothing based neural network architecture for traffic state estimationcited by 3
  7. 2022A dynamic multi-region MFD model for ride-sourcing with ridesplittingcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Learning to Learn the Macroscopic Fundamental Diagram using Physics-Informed and meta Machine Learning techniquescited by 1
  2. 2025Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless lp Norm Solution for Fast Adversarial Trainingcited by 0
  3. 2025FlowMixer: A Depth-Agnostic Neural Architecture for Interpretable Spatiotemporal Forecastingcited by 0