DeepXDE is a scientific machine learning library and deep learning PDE solver used to compute solutions for forward and inverse ordinary, partial, and integro-differential equations. It functions as a physics-informed neural network library that embeds physical laws and boundary conditions directly into the neural network loss function.
The project provides a deep operator network framework for learning operator mappings that approximate relationships between functions in multiphysics problems. It is implemented as a multi-backend tensor library, allowing the system to switch between different tensor backends for hardware-accelerated numerical operations.
The library's capabilities cover automatic differentiation, boundary condition enforcement, and the definition of complex geometries using constructive solid geometry. It also includes tools for multi-fidelity data modeling, prediction uncertainty quantification, and distributed model training across multiple GPUs.