Corpus ID: 218673725

SciANN: A Keras wrapper for scientific computations and physics-informed deep learning using artificial neural networks

@article{Haghighat2020SciANNAK,
  title={SciANN: A Keras wrapper for scientific computations and physics-informed deep learning using artificial neural networks},
  author={E. Haghighat and R. Juanes},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.08803}
}
In this paper, we introduce SciANN, a Python package for scientific computing and physicsinformed deep learning using artificial neural networks. SciANN uses the widely used deeplearning packages Tensorflow and Keras to build deep neural networks and optimization models, thus inheriting many of Keras’s functionalities, such as batch optimization and model reuse for transfer learning. SciANN is designed to abstract neural network construction for scientific computations and solution and… Expand
Physics-Informed Deep-Learning for Scientific Computing
TLDR
Evaluating the PINN potential to replace or accelerate traditional approaches for solving linear systems, and how to integrate PINN with traditional scientific computing approaches, such as multigrid and Gauss-Seidel methods. Expand
A deep learning framework for solution and discovery in solid mechanics: linear elasticity
TLDR
It is found that honoring the physics leads to improved robustness: when trained only on a few parameters, the PINN model can accurately predict the solution for a wide range of parameters new to the network—thus pointing to an important application of this framework to sensitivity analysis and surrogate modeling. Expand
A nonlocal physics-informed deep learning framework using the peridynamic differential operator
TLDR
Nonlocal PDDO-PINN is applied to the solution and identification of material parameters in solid mechanics and, specifically, to elastoplastic deformation in a domain subjected to indentation by a rigid punch, for which the mixed displacement--traction boundary condition leads to localized deformation and sharp gradients in the solution. Expand
Eikonal Solution Using Physics-Informed Neural Networks
The eikonal equation is utilized across a wide spectrum of science and engineering disciplines. In seismology, it regulates seismic wave traveltimes needed for applications like source localization,Expand
Robust Data-Driven Discovery of Partial Differential Equations under Uncertainties
TLDR
Results of numerical case studies indicate that the governing PDEs of many canonical dynamical systems can be correctly identified using the proposed ψ-PDE method with highly noisy data. Expand
NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation framework
TLDR
The neural network solver methodology, the SimNet architecture, and the various features that are needed for effective solution of the PDEs are reviewed. Expand
SURFNet: Super-resolution of Turbulent Flows with Transfer Learning using Small Datasets
Deep Learning (DL) algorithms are emerging as a key alternative to computationally expensive CFD simulations. However, state-of-the-art DL approaches require large and highresolution training data toExpand
An End-to-End AI-Driven Simulation Framework
We present SimNet, an AI-driven multi-physics simulation framework aiming to accelerate simulations across a wide range of disciplines in science and engineering. Compared to traditional numericalExpand
Deep learning for solution and inversion of structural mechanics and vibrations
TLDR
This chapter presents the application of deep learning and physics-informed neural networks concerning structural mechanics and vibration problems concerningStructural mechanics and vibrations problems. Expand
An energy-based error bound of physics-informed neural network solutions in elasticity
TLDR
An energy-based a posteriori error bound is proposed for the physics-informed neural network solutions of elasticity problems that provides an upper bound of the global error of neural network discretization. Expand
...
1
2
...

References

SHOWING 1-10 OF 39 REFERENCES
Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
  • M. Raissi
  • Mathematics, Computer Science
  • J. Mach. Learn. Res.
  • 2018
TLDR
This work puts forth a deep learning approach for discovering nonlinear partial differential equations from scattered and potentially noisy observations in space and time by approximate the unknown solution as well as the nonlinear dynamics by two deep neural networks. Expand
A deep learning framework for solution and discovery in solid mechanics
TLDR
It is found that honoring the physics leads to improved robustness: when trained only on a few parameters, the PINN model can accurately predict the solution for a wide range of parameters new to the network---thus pointing to an important application of this framework to sensitivity analysis and surrogate modeling. Expand
TensorFlow: A system for large-scale machine learning
TLDR
The TensorFlow dataflow model is described and the compelling performance that Tensor Flow achieves for several real-world applications is demonstrated. Expand
A unified deep artificial neural network approach to partial differential equations in complex geometries
TLDR
This paper shows how to modify the backpropagation algorithm to compute the partial derivatives of the network output with respect to the space variables which is needed to approximate the differential operator. Expand
MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
TLDR
The API design and the system implementation of MXNet are described, and it is explained how embedding of both symbolic expression and tensor operation is handled in a unified fashion. Expand
Learning Parameters and Constitutive Relationships with Physics Informed Deep Neural Networks
We present a physics informed deep neural network (DNN) method for estimating parameters and unknown physics (constitutive relationships) in partial differential equation (PDE) models. We use PDEs inExpand
Automatic differentiation in machine learning: a survey
TLDR
By precisely defining the main differentiation techniques and their interrelationships, this work aims to bring clarity to the usage of the terms “autodiff’, “automatic differentiation”, and “symbolic differentiation" as these are encountered more and more in machine learning settings. Expand
Machine Learning for Fluid Mechanics
TLDR
Fundamental machine learning methodologies are outlined and their uses for understanding, modeling, optimizing, and controlling fluid flows are discussed and the strengths and limitations are addressed from the perspective of scientific inquiry. Expand
The Deep Ritz Method: A Deep Learning-Based Numerical Algorithm for Solving Variational Problems
TLDR
A deep learning-based method, the Deep Ritz Method, for numerically solving variational problems, particularly the ones that arise from partial differential equations, which is naturally nonlinear, naturally adaptive and has the potential to work in rather high dimensions. Expand
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
...
1
2
3
4
...