MACE: A Machine learning Approach to Chemistry Emulation

arXiv (Cornell University)

Abstract

The chemistry of an astrophysical environment is closely coupled to its dynamics, the latter often found to be complex. Hence, to properly model these environments a 3D context is necessary. However, solving chemical kinetics within a 3D hydro simulation is computationally infeasible for a even a modest parameter study. In order to develop a feasible 3D hydro-chemical simulation, the classical chemical approach needs to be replaced by a faster alternative. We present mace, a Machine learning Approach to Chemistry Emulation, as a proof-of-concept work on emulating chemistry in a dynamical environment. Using the context of AGB outflows, we have developed an architecture that combines the use of an autoencoder (to reduce the dimensionality of the chemical network) and a set of latent ordinary differential equations (that are solved to perform the temporal evolution of the reduced features). Training this architecture with an integrated scheme makes it possible to successfully reproduce a full chemical pathway in a dynamical environment. mace outperforms its classical analogue on average by a factor 26. Furthermore, its efficient implementation in PyTorch results in a sub-linear scaling with respect to the number of hydrodynamical simulation particles.

Authors 4

1. Silke Maes

   KU Leuven

   Affiliation as printed

   Institute of Astronomy , KU Leuven , Celestijnenlaan 200D , B-3001 Leuven , Belgium

2. F. De Ceuster

   KU Leuven

   Affiliation as printed

   Institute of Astronomy , KU Leuven , Celestijnenlaan 200D , B-3001 Leuven , Belgium

3. Marie Van de Sande Aachen Leiden Observatory

   Leiden University · University of Leeds · Leiden Observatory

   Affiliation as printed

   Leiden Observatory , Leiden University , PO Box 9513 , 2300 RA Leiden , The Netherlands

   School of Physics and Astronomy , University of Leeds , Leeds LS2 9JT , United Kingdom

4. L. Decin

   University of Leeds · KU Leuven

   Affiliation as printed

   Institute of Astronomy , KU Leuven , Celestijnenlaan 200D , B-3001 Leuven , Belgium

   School of Chemistry , University of Leeds , Leeds LS2 9JT , United Kingdom