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

Abstract

In this paper, we introduce SciANN, a Python package for scientific computing and physics-informed deep learning using artificial neural networks. SciANN uses the widely used deep-learning 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 discovery of partial differential equations (PDE) using the physics-informed neural networks (PINN) architecture, therefore providing the flexibility to set up complex functional forms. We illustrate, in a series of examples, how the framework can be used for curve fitting on discrete data, and for solution and discovery of PDEs in strong and weak forms. We summarize the features currently available in SciANN, and also outline ongoing and future developments.

References in corpus (15)

• TensorFlow: A system for large-scale machine learning
• End to End Learning for Self-Driving Cars
• Machine Learning for Fluid Mechanics
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Facial Expression Analysis under Partial Occlusion: A Survey
• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• A unified deep artificial neural network approach to partial differential equations in complex geometries
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• Variational Physics-Informed Neural Networks For Solving Partial Differential Equations
• Learning Constitutive Relations using Symmetric Positive Definite Neural Networks
• Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data
• A deep learning framework for solution and discovery in solid mechanics
• Learning Parameters and Constitutive Relationships with Physics Informed Deep Neural Networks
• Numerical Gaussian Processes for Time-dependent and Non-linear Partial Differential Equations
• A machine learning accelerated FE${}^2$ homogenization algorithm for elastic solids

Cited by in corpus (44)

• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture
• Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
• PINNeik: Eikonal solution using physics-informed neural networks
• Physics-informed neural network simulation of multiphase poroelasticity using stress-split sequential training
• Deep Learning in Deterministic Computational Mechanics
• A nonlocal physics-informed deep learning framework using the peridynamic differential operator
• A Data-Driven Approach to Full-Field Damage and Failure Pattern Prediction in Microstructure-Dependent Composites using Deep Learning
• CCSNet: a deep learning modeling suite for CO${}_2$ storage
• Mixed formulation of physics-informed neural networks for thermo-mechanically coupled systems and heterogeneous domains
• Learning in Sinusoidal Spaces with Physics-Informed Neural Networks
• Physics-informed neural network solution of thermo-hydro-mechanical (THM) processes in porous media
• Magnetostatics and micromagnetics with physics informed neural networks
• Physics-informed machine learning for building performance simulation-A review of a nascent field
• Inverse modeling of nonisothermal multiphase poromechanics using physics-informed neural networks
• Conditional physics informed neural networks
• Physics-informed neural networks for one-dimensional sound field predictions with parameterized sources and impedance boundaries
• A Physics-Informed Neural Network approach for compartmental epidemiological models
• Latent Map Gaussian Processes for Mixed Variable Metamodeling
• PINNtomo: Seismic tomography using physics-informed neural networks
• An unsupervised latent/output physics-informed convolutional-LSTM network for solving partial differential equations using peridynamic differential operator
• A finite element-based physics-informed operator learning framework for spatiotemporal partial differential equations on arbitrary domains
• Energy-based error bound of physics-informed neural network solutions in elasticity
• On Physics-Informed Neural Networks for Quantum Computers
• NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation framework
• Physics-aware deep neural networks for surrogate modeling of turbulent natural convection
• RAR-PINN algorithm for the data-driven vector-soliton solutions and parameter discovery of coupled nonlinear equations
• Deep learning for solution and inversion of structural mechanics and vibrations
• Probabilistic model-error assessment of deep learning proxies: an application to real-time inversion of borehole electromagnetic measurements
• Neural networks: solving the chemistry of the interstellar medium
• IDRLnet: A Physics-Informed Neural Network Library
• Physics-Informed Holomorphic Neural Networks (PIHNNs): Solving Linear Elasticity Problems
• Physics-informed neural networks for learning the homogenized coefficients of multiscale elliptic equations
• A mixed formulation for physics-informed neural networks as a potential solver for engineering problems in heterogeneous domains: comparison with finite element method
• TensorDiffEq: Scalable Multi-GPU Forward and Inverse Solvers for Physics Informed Neural Networks
• Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities
• N-Adaptive Ritz Method: A Neural Network Enriched Partition of Unity for Boundary Value Problems
• Counting the uncounted : estimating the unaccounted COVID-19 infections in India
• A composable autoencoder-based iterative algorithm for accelerating numerical simulations
• A Neural Solver for Variational Problems on CAD Geometries with Application to Electric Machine Simulation
• On Theory-training Neural Networks to Infer the Solution of Highly Coupled Differential Equations
• Sparse logistic regression for RR Lyrae vs binaries classification
• Predicting Stress in Two-phase Random Materials and Super-Resolution Method for Stress Images by Embedding Physical Information