jinns: a JAX Library for Physics-Informed Neural Networks
This is an incremental contribution that offers a new tool for researchers and practitioners in computational science and engineering to implement physics-informed neural networks more easily.
The authors introduced jinns, a JAX-based library for physics-informed neural networks to address forward and inverse problems and meta-model learning, providing an efficient framework with baseline models and tutorials for prototyping real-world applications.
jinns is an open-source Python library for physics-informed neural networks, built to tackle both forward and inverse problems, as well as meta-model learning. Rooted in the JAX ecosystem, it provides a versatile framework for efficiently prototyping real-problems, while easily allowing extensions to specific needs. Furthermore, the implementation leverages existing popular JAX libraries such as equinox and optax for model definition and optimisation, bringing a sense of familiarity to the user. Many models are available as baselines, and the documentation provides reference implementations of different use-cases along with step-by-step tutorials for extensions to specific needs. The code is available on Gitlab https://gitlab.com/mia_jinns/jinns.