Machine-guided Exploration and Calibration of Astrophysical Simulations

TL;DR

This paper introduces a machine learning-based method for calibrating astrophysical simulation models, improving convergence with observations and between different simulation codes, demonstrated through cosmological and galaxy simulations.

Contribution

The authors develop a novel machine learning approach using active learning and neural density estimators for calibrating sub-grid models in astrophysical simulations, achieving significant improvements over manual methods.

Findings

Achieved over threefold improvement in calibration accuracy.

Enhanced agreement with observed baryon content in Milky-Way-sized halos.

Improved consistency in metal transport parameters across simulation codes.

Abstract

We apply a novel method with machine learning to calibrate sub-grid models within numerical simulation codes to achieve convergence with observations and between different codes. It utilizes active learning and neural density estimators. The hyper parameters of the machine are calibrated with a well-defined projectile motion problem. Then, using a set of 22 cosmological zoom simulations, we tune the parameters of a popular star formation and feedback model within Enzo to match simulations. The parameters that are adjusted include the star formation efficiency, coupling of thermal energy from stellar feedback, and volume into which the energy is deposited. This number translates to a factor of more than three improvements over manual calibration. Despite using fewer simulations, we obtain a better agreement to the observed baryon makeup of a Milky-Way (MW) sized halo. Switching to a different strategy, we improve the consistency of the recommended parameters from the machine. Given the success of the calibration, we then apply the technique to reconcile metal transport between grid-based and particle-based simulation codes using an isolated galaxy. It is an improvement over manual exploration while hinting at a less known relation between the diffusion coefficient and the metal mass in the halo region. The exploration and calibration of the parameters of the sub-grid models with a machine learning approach is concluded to be versatile and directly applicable to different problems.