Physics-Informed Neural Networks promise to revolutionize science and engineering practice, by introducing domain-aware deep machine learning models into scientific computation. Several software suites have emerged to make the implementation and usage of these architectures available to the research and industry communities. Here we introduce\linebreak TensorDiffEq, built on Tensorflow 2.x, which presents an intuitive Keras-like interface for problem domain definition, model definition, and solution of forward and inverse problems using physics-aware deep learning methods. TensorDiffEq takes full advantage of Tensorflow 2.x infrastructure for deployment on multiple GPUs, allowing the implementation of large high-dimensional and complex models. Simultaneously, TensorDiffEq supports the Keras API for custom neural network architecture definitions. In the case of smaller or simpler models, the package allows for rapid deployment on smaller-scale CPU platforms with negligible changes to the implementation scripts. We demonstrate the basic usage and capabilities of TensorDiffEq in solving forward, inverse, and data assimilation problems of varying sizes and levels of complexity. The source code is available at https://github.com/tensordiffeq.

中文翻译：

---

TensorDiffEq：用于物理信息神经网络的可扩展多GPU正向和反向求解器

物理信息神经网络有望通过将领域感知的深度机器学习模型引入科学计算中来革新科学和工程实践。已经出现了一些软件套件，以使研究和行业团体可以使用和使用这些体系结构。在这里，我们介绍基于Tensorflow 2.x构建的\ linebreak TensorDiffEq，它提供了直观的类似Keras的界面，用于使用物理感知的深度学习方法来解决问题域定义，模型定义以及正向和反向问题的解决方案。TensorDiffEq充分利用Tensorflow 2.x基础架构在多个GPU上进行部署，从而可以实现大型的高维和复杂模型。同时，TensorDiffEq支持Keras API用于自定义神经网络体系结构定义。对于较小或更简单的模型，该软件包允许对较小规模的CPU平台进行快速部署，而对实现脚本的更改可以忽略不计。我们展示了TensorDiffEq在解决大小，复杂度不同的正向，反向和数据同化问题中的基本用法和功能。可从https://github.com/tensordiffeq获得源代码。