Emulating Cosmic Structure Formation with a Lagrangian Neural Cellular Automaton
The LNCA is introduced, a hybrid deep learning framework that can be applied to emulate structure formation as a local, iterative dynamical process on a comoving lattice, and constrain the model to produce complete trajectories, not just final states, by adopting an equivariant cellular automaton architecture.
Cooper Jacobus, Beatriz Tucci, O. Philcox
· arXiv.org · 0 citations