GRINN: A Physics-Informed Neural Network for solving hydrodynamic systems in the presence of self-gravity

TL;DR

GRINN introduces a physics-informed neural network that efficiently models 3D self-gravitating hydrodynamic systems, achieving high accuracy and better scalability compared to traditional grid-based methods in astrophysics simulations.

Contribution

This paper presents GRINN, a novel PINN-based code specifically designed for 3D self-gravitating hydrodynamics, demonstrating improved scalability and comparable accuracy to grid codes.

Findings

GRINN matches linear solutions within 1% accuracy.

GRINN's computation time does not scale with dimensions.

In 3D, GRINN is an order of magnitude faster than grid codes with similar accuracy.

Abstract

Modeling self-gravitating gas flows is essential to answering many fundamental questions in astrophysics. This spans many topics including planet-forming disks, star-forming clouds, galaxy formation, and the development of large-scale structures in the Universe. However, the nonlinear interaction between gravity and fluid dynamics offers a formidable challenge to solving the resulting time-dependent partial differential equations (PDEs) in three dimensions (3D). By leveraging the universal approximation capabilities of a neural network within a mesh-free framework, physics informed neural networks (PINNs) offer a new way of addressing this challenge. We introduce the gravity-informed neural network (GRINN), a PINN-based code, to simulate 3D self-gravitating hydrodynamic systems. Here, we specifically study gravitational instability and wave propagation in an isothermal gas. Our results match a linear analytic solution to within 1\% in the linear regime and a conventional grid code solution to within 5\% as the disturbance grows into the nonlinear regime. We find that the computation time of the GRINN does not scale with the number of dimensions. This is in contrast to the scaling of the grid-based code for the hydrodynamic and self-gravity calculations as the number of dimensions is increased. Our results show that the GRINN computation time is longer than the grid code in one- and two- dimensional calculations but is an order of magnitude lesser than the grid code in 3D with similar accuracy. Physics-informed neural networks like GRINN thus show promise for advancing our ability to model 3D astrophysical flows.