Baryon density extraction and isotropy analysis of cosmic microwave background using deep learning

Abstract

The discovery of cosmic microwave background (CMB) was a paradigm shift in the study and fundamental understanding of the early Universe and also the Big Bang phenomenon. Cosmic microwave background is one of the richest and intriguing sources of information available to cosmologists and one parameter of special interest is baryon density of the Universe. Baryon density can be primarily estimated by analyzing CMB data or through the study of big bang nucleosynthesis (BBN). Hence, it is necessary that both of the results found through the two methods are in agreement with each other. Although there are some well established statistical methods for the analysis of CMB to estimate baryon density, here we explore the use of deep learning in this respect. We correlate the baryon density obtained from the power spectrum of simulated CMB temperature maps with the corresponding map image and form the dataset for training the neural network model. We analyze the accuracy with which the model is able to predict the results from a relatively abstract dataset considering the fact that CMB is a Gaussian random field. CMB is anisotropic due to temperature fluctuations at small scales but on a larger scale CMB is considered isotropic, here we analyze the isotropy of CMB by training the model with CMB maps centered at different galactic coordinates and compare the predictions of neural network models.

On the application of machine learning in astronomy and astrophysics: A text‐mining‐based scientometric analysis

“…As demonstrated by the term “simulations,” this field of study works with mathematical models that use computer simulations to consider the corresponding initial conditions and gravitational physical mechanisms, generating a large volume of data (generally, relative to evolution processes) that can be used for prediction and analysis tasks (Poczos, 2018; Rodríguez et al, 2018; Villaescusa‐Navarro et al, 2021). Other examples of areas of cosmology in which AI/ML find use are the study of dark matter (Bertone et al, 2017; Lucie‐Smith et al, 2018; Stephon et al, 2020) and its halos surrounding galaxies (Agarwal et al, 2018; Lucie‐Smith et al, 2019; Nadler et al, 2018), dark energy (Arjona & Nesseris, 2020a; Escamilla‐Rivera et al, 2020), models of the creation and expansion of the universe (Arjona & Nesseris, 2020b), the cosmic microwave background (CMB) (Arjona, 2020; Mishra & Reddy, 2020), and the total mass of galaxies (considering dark matter) (McLeod et al, 2017). At this point, generative adversarial networks (GAN) are worth mentioning; since they are capable of simplifying, or even eliminating, the use of costly simulations in cosmology, they constitute one of the most promising ML models in astronomy/astrophysics (Diakogiannis et al, 2019).…”