SPINN: Advancing Cosmological Simulations of Fuzzy Dark Matter with Physics Informed Neural Networks

TL;DR

This paper introduces SPINN, a Physics-Informed Neural Network approach for simulating gravitational collapse of Fuzzy Dark Matter, achieving accurate results and offering a scalable alternative to traditional methods.

Contribution

The work presents the first application of PINNs to solve nonlinear Schrödinger-Poisson equations for FDM, demonstrating accurate and scalable simulations in 1D and 3D.

Findings

Accurate predictions of mass conservation and density profiles.

Validation against analytical and numerical benchmarks.

Potential for scalable modeling of astrophysical systems.

Abstract

Physics-Informed Neural Networks (PINNs) have emerged as a powerful tool for solving differential equations by integrating physical laws into the learning process. This work leverages PINNs to simulate gravitational collapse, a critical phenomenon in astrophysics and cosmology. We introduce the Schr\"odinger-Poisson informed neural network (SPINN) which solve nonlinear Schr\"odinger-Poisson (SP) equations to simulate the gravitational collapse of Fuzzy Dark Matter (FDM) in both 1D and 3D settings. Results demonstrate accurate predictions of key metrics such as mass conservation, density profiles, and structure suppression, validating against known analytical or numerical benchmarks. This work highlights the potential of PINNs for efficient, possibly scalable modeling of FDM and other astrophysical systems, overcoming the challenges faced by traditional numerical solvers due to the non-linearity of the involved equations and the necessity to resolve multi-scale phenomena especially resolving the fine wave features of FDM on cosmological scales.