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

TL;DR

SciANN is a Python package that simplifies the use of neural networks for scientific computing and physics-informed learning, leveraging TensorFlow and Keras for flexible PDE solutions and discovery.

Contribution

It introduces SciANN, a user-friendly wrapper that abstracts neural network construction for scientific problems, enabling efficient PDE solving and discovery using PINNs.

Findings

Effective for curve fitting on discrete data

Able to solve PDEs in strong and weak forms

Supports complex functional forms for scientific computations

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.