Physics-Informed Deep Learning for Traffic State Estimation: A Hybrid Paradigm Informed By Second-Order Traffic Models

Shi, Rongye; Mo, Zhaobin; Di, Xuan

doi:10.1609/aaai.v35i1.16132

Cited by 54 publications

(26 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many recent studies have proposed to integrate physics-based modeling approaches with state-of-the-art deep learning techniques, giving birth to a field called "Physics-Guided Deep Learning". One can introduce additional physics-based penalty in loss function of neural networks (Shi, Mo, and Di 2021). Some efforts also lie in combining physics-based models with deep learning.…”

Section: Related Workmentioning

confidence: 99%

STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction

Wang

Jiang

et al. 2022

AAAI

View full text Add to dashboard Cite

High-performance traffic flow prediction model designing, a core technology of Intelligent Transportation System, is a long-standing but still challenging task for industrial and academic communities. The lack of integration between physical principles and data-driven models is an important reason for limiting the development of this field. In the literature, physics-based methods can usually provide a clear interpretation of the dynamic process of traffic flow systems but are with limited accuracy, while data-driven methods, especially deep learning with black-box structures, can achieve improved performance but can not be fully trusted due to lack of a reasonable physical basis. To bridge the gap between purely data-driven and physics-driven approaches, we propose a physics-guided deep learning model named Spatio-Temporal Differential Equation Network (STDEN), which casts the physical mechanism of traffic flow dynamics into a deep neural network framework. Specifically, we assume the traffic flow on road networks is driven by a latent potential energy field (like water flows are driven by the gravity field), and model the spatio-temporal dynamic process of the potential energy field as a differential equation network. STDEN absorbs both the performance advantage of data-driven models and the interpretability of physics-based models, so is named a physics-guided prediction model. Experiments on three real-world traffic datasets in Beijing show that our model outperforms state-of-the-art baselines by a significant margin. A case study further verifies that STDEN can capture the mechanism of urban traffic and generate accurate predictions with physical meaning. The proposed framework of differential equation network modeling may also cast light on other similar applications.

show abstract

Section: Related Workmentioning

confidence: 99%

STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction

Wang

Jiang

et al. 2022

AAAI

View full text Add to dashboard Cite

show abstract

“…Tis problem has both a physics-informed neural network and a physicsuninformed neural network. Whereafter, [5] proposed a hybrid framework, a physics-informed deep learning model, to combine second-order trafc fow models and neural networks for the TSE. And they used experiments to demonstrate the proposed model in terms of data efciency and estimation accuracy.…”

Section: Hybrid Of Trafc Flow Models and Neural Networkmentioning

confidence: 99%

“…Te methods of estimating trafc conditions can be briefy divided into two main approaches: model-driven and datadriven. References [4,5] have defned the data-driven method to infer trafc states based on the dependence learned from historical data using statistical or machine learning methods, such as convolutional neural networks (CNN), and long-term memory (LSTM) [6]. Te modeldriven approach is based on a priori knowledge of trafc dynamics, usually described by a physical model, e.g., the Lighthill-Whitham-Richards (LWR) models [7,8], and the cell transmission model (CTM) [9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Incorporating Traffic Flow Model into A Deep Learning Method for Traffic State Estimation: A Hybrid Stepwise Modeling Framework

Pan

Guo²,

Chen

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

Traffic state estimation (TSE), which reconstructs the traffic variables (e.g., speed, flow) on road segments using partially observed data, plays an essential role in intelligent transportation systems. Generally, traffic estimation problems can be divided into two categories: model-driven approaches and data-driven approaches. The model-driven method is commonly used to solve TSE efficiently and calibrate the parameters of these models. The data-driven method requires a large amount of historical observed traffic data in order to improve performance accurately. In order to combine the advantages of model-driven and data-driven methods, this paper proposed a hybrid framework incorporating the traffic flow model into deep learning (TFMDL) modeling that contains both model-driven and data-driven components. This paper focuses on highway TSE with observed data from loop detectors. We build a hybrid cost function to adjust the weights of model-driven and data-driven proportions. We then evaluate the proposed framework using the open-access performance measurement system (PMS) dataset on a corridor of US I-405 in Los Angeles, California. The experimental results show the advantages of the proposed TFMDL approach in performing better than several benchmark models in terms of estimation accuracy and data efficiency.

show abstract

“…Hybrid methods combine desirable features from both model-driven and data-driven approaches in order to ensure accurate results and reduce data requirements [27], [28]. A new framework in the deep learning literature, namely physics-informed deep learning, has gain significant attention the past few years with promising results as these physics-informed regularisers reduce the space of feasible solutions and approximate solutions that are consistent with the chosen models using a limited amount of data (see for example, [29], [30], [31], [32]). Despite the recent success of physics-informed learning some studies have shown that such methods might fail to train [33] or could be computationally expensive [34].…”

Section: Introductionmentioning

confidence: 99%

Bayesian Traffic State Estimation Using Extended Floating Car Data

Englezou

Victor

Christos

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Traffic state estimation is a challenging task due to the collection of sparse and noisy measurements from specific points of the traffic network. The emergence of Connected and Automated Vehicles (CAVs) provides new capabilities for traffic state estimation using extended floating car data such as position, speed and spacing information. In this work we propose a Bayesian Traffic State Estimation (BTSE) methodology for estimating the traffic density based on extended floating car data. BTSE utilizes the Bayesian paradigm to express any prior information to derive probability distributions of the traffic density of different road segments of the traffic network. Two variations of the BTSE methodology are developed to handle the offline and online estimation problem. The BTSE methodology is evaluated both using realistic SUMO microsimulations for M25 Highway, London, U.K., and a real-life vehicle-trajectory dataset from German highways, extracted from videos recorded by drones. The efficiency and accuracy of the BTSE methodology is compared to an existing methodology in the literature. We present results for the estimation performance of the methods showing that the Bayesian methodology consistently results in lower mean absolute percentage error than the compared literature method. The BTSE methodology yields high-quality estimation results even for a low penetration rate of CAVs (e.g. 5%).

show abstract

Physics-Informed Deep Learning for Traffic State Estimation: A Hybrid Paradigm Informed By Second-Order Traffic Models

Cited by 54 publications

References 12 publications

STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction

STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction

Incorporating Traffic Flow Model into A Deep Learning Method for Traffic State Estimation: A Hybrid Stepwise Modeling Framework

Bayesian Traffic State Estimation Using Extended Floating Car Data

Contact Info

Product

Resources

About