TrafficFlowGAN: Physics-Informed Flow Based Generative Adversarial Network for Uncertainty Quantification

Mo, Zhaobin; Fu, Yongjie; Xu, Daran; Di, Xuan

doi:10.1007/978-3-031-26409-2_20

Cited by 8 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accordingly, neither model-driven nor data-driven approaches alone suffice to predict such behaviors with high accuracy and robustness. Therefore, we strongly believe that a hybrid method, which leverages the advantages of both model-driven and data-driven approaches, is promising [9,10].…”

Section: Scope Of This Surveymentioning

confidence: 99%

“…The EKF makes use of the three parameter-based LWR as the core physics when conducting the estimation. The NN only contains the PUNN component in Figure 6, and uses the first term in Equation (10) as the training loss. Among the PIDL variants, the PIDL-LWR and PIDL-ARZ are the PIDL models that encode the three parameter-based LWR and Greenshields-based ARZ, respectively, into the PICG.…”

Section: Real-world Data Validationmentioning

confidence: 99%

“…Transition from pure physics-driven to data-driven TSE models: The contributions of the physics-driven and data-driven components can be controlled by tuning the hyperparameters α and β in Equation (10). Figure 10 shows how the optimal β/α ratio changes as the data size increases.…”

Section: Real-world Data Validationmentioning

confidence: 99%

“…is the predicted traffic state, and ŝ is the ground-truth. With physics imposed, the generator loss carries the same form as Equation (10), and the data loss L o and boundary loss L b become:…”

Section: Physics-informed Generative Adversarial Network (Physgan)mentioning

confidence: 99%

See 3 more Smart Citations

Physics-Informed Deep Learning for Traffic State Estimation: A Survey and the Outlook

Shi

et al. 2023

Algorithms

View full text Add to dashboard Cite

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 (DNNs), 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 the physics is encoded into DNNs and how the physics and data components are represented. In this paper, we offer an overview of 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.

show abstract

Section: Scope Of This Surveymentioning

confidence: 99%

Section: Real-world Data Validationmentioning

confidence: 99%

Section: Real-world Data Validationmentioning

confidence: 99%

Section: Physics-informed Generative Adversarial Network (Physgan)mentioning

confidence: 99%

See 2 more Smart Citations

Physics-Informed Deep Learning for Traffic State Estimation: A Survey and the Outlook

Shi

et al. 2023

Algorithms

View full text Add to dashboard Cite

show abstract

“…Subsequent research is developed based on such methodology, e.g., Peek Into The Future (PITF) [28] and State-Refinement LSTM (SR-LSTM) [29]. Another interesting direction is to use the Generative Adversarial framework [23,[30][31][32][33], e.g., Social GAN [34] and Sophie [35].…”

Section: Introductionmentioning

confidence: 99%

InfoSTGCAN: An Information-Maximizing Spatial-Temporal Graph Convolutional Attention Network for Heterogeneous Human Trajectory Prediction

Ruan,

2024

Computers

Self Cite

View full text Add to dashboard Cite

Predicting the future trajectories of multiple interacting pedestrians within a scene has increasingly gained importance in various fields, e.g., autonomous driving, human–robot interaction, and so on. The complexity of this problem is heightened due to the social dynamics among different pedestrians and their heterogeneous implicit preferences. In this paper, we present Information Maximizing Spatial-Temporal Graph Convolutional Attention Network (InfoSTGCAN), which takes into account both pedestrian interactions and heterogeneous behavior choice modeling. To effectively capture the complex interactions among pedestrians, we integrate spatial-temporal graph convolution and spatial-temporal graph attention. For grasping the heterogeneity in pedestrians’ behavior choices, our model goes a step further by learning to predict an individual-level latent code for each pedestrian. Each latent code represents a distinct pattern of movement choice. Finally, based on the observed historical trajectory and the learned latent code, the proposed method is trained to cover the ground-truth future trajectory of this pedestrian with a bi-variate Gaussian distribution. We evaluate the proposed method through a comprehensive list of experiments and demonstrate that our method outperforms all baseline methods on the commonly used metrics, Average Displacement Error and Final Displacement Error. Notably, visualizations of the generated trajectories reveal our method’s capacity to handle different scenarios.

show abstract

Ensemble Learning with Physics-Informed Neural Networks for Harsh Time Series Analysis

Kayisu,

Fasouli,

Kambale

et al. 2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

TrafficFlowGAN: Physics-Informed Flow Based Generative Adversarial Network for Uncertainty Quantification

Cited by 8 publications

References 15 publications

Physics-Informed Deep Learning for Traffic State Estimation: A Survey and the Outlook

Physics-Informed Deep Learning for Traffic State Estimation: A Survey and the Outlook

InfoSTGCAN: An Information-Maximizing Spatial-Temporal Graph Convolutional Attention Network for Heterogeneous Human Trajectory Prediction

Ensemble Learning with Physics-Informed Neural Networks for Harsh Time Series Analysis

Contact Info

Product

Resources

About