Neural Networks for cosmological model selection and feature importance using Cosmic Microwave Background data

TL;DR

This paper demonstrates that neural networks can effectively differentiate between cosmological models using Planck CMB data, highlighting the potential of machine learning in future cosmological analyses.

Contribution

The study applies neural networks and interpretability methods to distinguish between ΛCDM and alternative cosmological models using Planck data.

Findings

Neural networks successfully differentiate between models.

SHAP values identify key features influencing model decisions.

Archival data remains valuable for testing new algorithms.

Abstract

The measurements of the temperature and polarisation anisotropies of the Cosmic Microwave Background (CMB) by the ESA Planck mission have strongly supported the current concordance model of cosmology. However, the latest cosmological data release from ESA Planck mission still has a powerful potential to test new data science algorithms and inference techniques. In this paper, we use advanced Machine Learning (ML) algorithms, such as Neural Networks (NNs), to discern among different underlying cosmological models at the angular power spectra level, using both temperature and polarisation Planck 18 data. We test two different models beyond $\Lambda$CDM: a modified gravity model: the Hu-Sawicki model, and an alternative inflationary model: a feature-template in the primordial power spectrum. Furthermore, we also implemented an interpretability method based on SHAP values to evaluate the learning process and identify the most relevant elements that drive our architecture to certain outcomes. We find that our NN is able to distinguish between different angular power spectra successfully for both alternative models and $\Lambda$CDM. We conclude by explaining how archival scientific data has still a strong potential to test novel data science algorithms that are interesting for the next generation of cosmological experiments.