Phy-Taylor: Physics-Model-Based Deep Neural Networks

  title={Phy-Taylor: Physics-Model-Based Deep Neural Networks},
  author={Yanbing Mao and Lui Raymond Sha and Huajie Shao and Yuliang Gu and Qixin Wang and Tarek F. Abdelzaher},
Purely data-driven deep neural networks (DNNs) applied to physical engineering systems can infer relations that violate physics laws, thus leading to unexpected consequences. To address this challenge, we propose a physics-model-based DNN framework, called Phy-Taylor, that accelerates learning compliant representations with physical knowledge. The Phy-Taylor framework makes two key contributions; it introduces a new architectural physics-compatible neural network (PhN), and features a novel… 

The Methodological Pitfall of Dataset-Driven Research on Deep Learning: An IoT Example

A dangerous pitfall in the state-of-the-art evaluation methodology of deep learning algorithms results in deceptively good evaluation outcomes on test datasets, whereas the underlying algorithms remain prone to catastrophic failure in practice.



Physics-Guided Deep Learning for Dynamical Systems: A survey

A structured overview of existing methodologies of integrating prior physical knowledge or physics-based modeling into deep learning and discuss the emerging opportunities is provided.

PhyNet: Physics Guided Neural Networks for Particle Drag Force Prediction in Assembly

This paper proposes PhyNet, a deep learning model using physics- guided structural priors and physics-guided aggregate supervision for modeling the drag forces acting on each particle in a Computational Fluid Dynamics-Discrete Element Method (CFD-DEM).

Physics Constrained Learning for Data-driven Inverse Modeling from Sparse Observations

Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling

A novel framework, termed as physics-guided neural network (PGNN), leverages the output of physics-based model simulations along with observational features to generate predictions using a neural network architecture to ensure better generalizability as well as physical consistency of results.

Physics-informed neural networks with hard constraints for inverse design

This work proposes a new deep learning method—physics-informed neural networks with hard constraints (hPINNs)—for solving topology optimization and demonstrates the effectiveness of hPINN for a holography problem in optics and a fluid problem of Stokes flow.

Towards Physics-informed Deep Learning for Turbulent Flow Prediction

This paper proposes a hybrid approach to predict turbulent flow by learning its highly nonlinear dynamics from spatiotemporal velocity fields of large-scale fluid flow simulations of relevance to turbulence modeling and climate modeling by marrying two well-established turbulent flow simulation techniques with deep learning.

HybridNet: Integrating Model-based and Data-driven Learning to Predict Evolution of Dynamical Systems

The experimental results on two dynamical systems, namely, heat convection-diffusion system, and fluid dynamical system, demonstrate that the HybridNet produces higher accuracy than the state-of-the-art deep learning based approach.

Augmenting physical models with deep networks for complex dynamics forecasting

The APHYNITY framework is introduced, a principled approach for augmenting incomplete physical dynamics described by differential equations with deep data-driven models and can efficiently leverage approximate physical models to accurately forecast the evolution of the system and correctly identify relevant physical parameters.

Deep Learning of Subsurface Flow via Theory-guided Neural Network

Incorporating Symmetry into Deep Dynamics Models for Improved Generalization

This work proposes to improve accuracy and generalization by incorporating symmetries into deep neural networks by employing a variety of methods each tailored to enforce a different symmetry.