Enhancing Cosmological Model Selection with Interpretable Machine Learning
- 31 January 2025
- journal article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 134 (4) , 041002
Abstract
We propose a novel approach using neural networks (NNs) to differentiate between cosmological models, and implemented lime as an interpretability approach to identify the key features influencing our model's decisions. We show the potential of NNs to enhance the extraction of meaningful information from cosmological large-scale structure data, based on current galaxy-clustering survey specifications, for the cosmological constant and cold dark matter (ΛCDM) model and the Hu-Sawicki f(R) model. We find that the NN can successfully distinguish between ΛCDM and the f(R) models, by predicting the correct model with approximately 97% overall accuracy, thus demonstrating that NNs can maximize the potential of current and next generation surveys to probe for deviations from general relativity.Keywords
All Related Versions
Funding Information
- European Space Agency
- Agencia Estatal de Investigación (PID2021-123012NB-C43)
- Ministerio de Ciencia e Innovación
- Comunidad de Madrid
- 'la Caixa' Foundation (LCF/BQ/DI22/11940033)
- Fondo Nacional de Desarrollo Científico y Tecnológico (1200171)
- IFT Centro de Excelencia Severo Ochoa (CEX2020-001007-S)
- Spanish Attraccion de Talento (2019-T1/TIC-13177)
This publication has 68 references indexed in Scilit:
- Challenges for
Λ
CDM: An updateNew Astronomy Reviews, 2022
- Cosmology intertwined: A review of the particle physics, astrophysics, and cosmology associated with the cosmological tensions and anomaliesJournal of High Energy Astrophysics, 2022
- Planck2018 resultsAstronomy & Astrophysics, 2020
- Jet substructure at the Large Hadron Collider: A review of recent advances in theory and machine learningPhysics Reports, 2020
- Star formation rates and stellar masses from machine learningAstronomy & Astrophysics, 2019
- Deep-learning top taggers or the end of QCD?Journal of High Energy Physics, 2017
- Baryon acoustic oscillations in the Lyαforest of BOSS DR11 quasarsAstronomy & Astrophysics, 2015
- Extended Theories of GravityPhysics Reports, 2011
- The Invisible Universe: Dark Matter and Dark Energy2007
- A new type of isotropic cosmological models without singularityPhysics Letters B, 1980