Our new paper 'Dreaming of Electrical Waves: Generative Modelling of Cardiac Excitation Waves using Diffusion Models' (Link) was published in APL Machine Learning. In this numerical study, we explored diffusion models, a type of generative AI, for the modeling of reentrant electrophysiological wave phenomena which occur in heart muscle tissue during atrial or ventricular fibrillation. Our results suggest that diffusion models could present an alternative approach to conventional biophysical modeling of these phenomena as well as many other biophysical processes. Congratulations to Tanish Baranwal and Jan Lebert! A preprint of the paper is also available on arXiv.

APL Machine Learning is a new interdisciplinary journal published by the American Institute of Physics via AIP Publishing. The journal features research for two communities: researchers who use machine learning (ML) and data-driven approaches for physical sciences, and researchers from these disciplines who work on novel concepts and algorithms relevant for the development of better ML and AI technologies.