IDRLnet: A Physics-Informed Neural Network Library
This is an incremental contribution that provides a domain-specific tool for researchers and practitioners in scientific computing using PINNs.
The authors tackled the need for a systematic toolbox for Physics-Informed Neural Networks (PINNs) by introducing IDRLnet, a Python library that provides a structured framework for modeling and solving PDE-based forward and inverse problems, with features like handling geometric objects, noisy data, and easy integration of new PINN variants.
Physics Informed Neural Network (PINN) is a scientific computing framework used to solve both forward and inverse problems modeled by Partial Differential Equations (PDEs). This paper introduces IDRLnet, a Python toolbox for modeling and solving problems through PINN systematically. IDRLnet constructs the framework for a wide range of PINN algorithms and applications. It provides a structured way to incorporate geometric objects, data sources, artificial neural networks, loss metrics, and optimizers within Python. Furthermore, it provides functionality to solve noisy inverse problems, variational minimization, and integral differential equations. New PINN variants can be integrated into the framework easily. Source code, tutorials, and documentation are available at \url{https://github.com/idrl-lab/idrlnet}.