Physics-Informed Deep Learning For Traffic State Estimation: A Survey and the Outlook
arXiv:2303.02063 · doi:10.3390/a16060305
Abstract
For its robust predictive power (compared to pure physics-based models) and sample-efficient training (compared to pure deep learning models), physics-informed deep learning (PIDL), a paradigm hybridizing physics-based models and deep neural networks (DNN), has been booming in science and engineering fields. One key challenge of applying PIDL to various domains and problems lies in the design of a computational graph that integrates physics and DNNs. In other words, how physics are encoded into DNNs and how the physics and data components are represented. In this paper, we provide a variety of architecture designs of PIDL computational graphs and how these structures are customized to traffic state estimation (TSE), a central problem in transportation engineering. When observation data, problem type, and goal vary, we demonstrate potential architectures of PIDL computational graphs and compare these variants using the same real-world dataset.
References in corpus (31)
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- Congested Traffic States in Empirical Observations and Microscopic Simulations
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
- Neural Architecture Search: A Survey
- Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
- Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
- Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
- Deep Learning for Short-Term Traffic Flow Prediction
- Survey on Multi-Access Edge Computing for Internet of Things Realization
- Integrating Machine Learning and Multiscale Modeling: Perspectives, Challenges, and Opportunities in the Biological, Biomedical, and Behavioral Sciences
- Koopman invariant subspaces and finite linear representations of nonlinear dynamical systems for control
- Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
- Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
- Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
- Deep Learning of Vortex Induced Vibrations
- Discovering Symbolic Models from Deep Learning with Inductive Biases
- A Nonconvex Low-Rank Tensor Completion Model for Spatiotemporal Traffic Data Imputation
- A Physics-Informed Deep Learning Paradigm for Car-Following Models
- Low-Rank Autoregressive Tensor Completion for Spatiotemporal Traffic Data Imputation
- Meta-learning PINN loss functions
- A Physics-Informed Deep Learning Paradigm for Traffic State and Fundamental Diagram Estimation
- Comparative model accuracy of a data-fitted generalized Aw-Rascle-Zhang model
- STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction
- Normalizing field flows: Solving forward and inverse stochastic differential equations using physics-informed flow models
- A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation
- ADMM for Efficient Deep Learning with Global Convergence
- PID-GAN: A GAN Framework based on a Physics-informed Discriminator for Uncertainty Quantification with Physics
- On the Koopman operator of algorithms
- A non-cooperative meta-modeling game for automated third-party calibrating, validating, and falsifying constitutive laws with parallelized adversarial attacks
- Stabilizing Traffic via Autonomous Vehicles: A Continuum Mean Field Game Approach
- Learning-based State Reconstruction for a Scalar Hyperbolic PDE under noisy Lagrangian Sensing