Neural networks: solving the chemistry of the interstellar medium

Abstract

ABSTRACT Non-equilibrium chemistry is a key process in the study of the interstellar medium (ISM), in particular the formation of molecular clouds and thus stars. However, computationally, it is among the most difficult tasks to include in astrophysical simulations, because of the typically high (>40) number of reactions, the short evolutionary time-scales (about 104 times less than the ISM dynamical time), and the characteristic non-linearity and stiffness of the associated ordinary differential equations system (ODEs). In this proof of concept work, we show that Physics Informed Neural Networks (PINN) are a viable alternative to traditional ODE time integrators for stiff thermochemical systems, i.e. up to molecular hydrogen formation (9 species and 46 reactions). Testing different chemical networks in a wide range of densities (−2 < log n/cm−3 < 3) and temperatures (1 < log T/K < 5), we find that a basic architecture can give a comfortable convergence only for simplified chemical systems: to properly capture the sudden chemical and thermal variations, a Deep Galerkin Method is needed. Once trained (∼103 GPUhr), the PINN well reproduces the strong non-linear nature of the solutions (errors $\lesssim 10{{\ \rm per\ cent}}$) and can give speed-ups up to a factor of ∼200 with respect to traditional ODE solvers. Further, the latter have completion times that vary by about $\sim 30{{\ \rm per\ cent}}$ for different initial n and T, while the PINN method gives negligible variations. Both the speed-up and the potential improvement in load balancing imply that PINN-powered simulations are a very palatable way to solve complex chemical calculation in astrophysical and cosmological problems.