The paper describing the main functionalities of jwave is out on SoftwareX!

Comparison of a transcranial simulation in j-Wave against the widely used k-Wave. Adapted from [Aubry et al.]

j-Wave is a simulator based on JAX, that can solve time-varying and time-harmonic acoustic problems.

It supports automatic differentiation (and all of JAX fancy composable program transformations), making it a valuable tool for machine learning and scientific computing.

j-Wave is composed of modular components that can be easily customized and reused. while being compatible with some of the most popular machine learning libraries, such as JAX and TensorFlow. The accuracy of the simulator is evaluated against the widely used k-Wave toolbox and a cohort of acoustic simulation software.