Cosmology-informed neural networks to solve the background dynamics of the Universe

TL;DR

This paper demonstrates that neural networks can effectively solve the differential equations governing the Universe's background dynamics, providing accurate solutions that match traditional methods and facilitate parameter estimation from observational data.

Contribution

It introduces a neural network approach to solve cosmological differential equations and validates its accuracy and efficiency compared to numerical solvers.

Findings

Neural networks accurately reproduce solutions with at most 1% error.

The method yields parameter estimates consistent with literature.

Solutions are computationally efficient and suitable for statistical analysis.

Abstract

The field of machine learning has drawn increasing interest from various other fields due to the success of its methods at solving a plethora of different problems. An application of these has been to train artificial neural networks to solve differential equations without the need of a numerical solver. This particular application offers an alternative to conventional numerical methods, with advantages such as lower memory required to store solutions, parallelization, and, in some cases, a lower overall computational cost than its numerical counterparts. In this work, we train artificial neural networks to represent a bundle of solutions of the differential equations that govern the background dynamics of the Universe for four different models. The models we have chosen are $\Lambda \mathrm{CDM}$, the Chevallier-Polarski-Linder parametric dark energy model, a quintessence model with an exponential potential, and the Hu-Sawicki $f(R)$ model. We use the solutions that the networks provide to perform statistical analyses to estimate the values of each model's parameters with observational data; namely, estimates of the Hubble parameter from cosmic chronometers, type Ia supernovae data from the Pantheon compilation, and measurements from baryon acoustic oscillations. The results we obtain for all models match similar estimations done in the literature using numerical solvers. In addition, we estimate the error of the solutions that the trained networks provide by comparing them with the analytical solution when there is one, or to a high-precision numerical solution when there is not. Through these estimations we find that the error of the solutions is at most $\sim1\%$ in the region of the parameter space that concerns the $95\%$ confidence regions that we find using the data, for all models and all statistical analyses performed in this work.