In classical cosmological analysis of large-scale structure surveys with two-point functions, the parameter measurement precision is limited by several key degeneracies within the cosmology and astrophysics sectors. For cosmic shear, clustering amplitude ${\sigma }_8$ and matter density ${\mathrm{\Omega }}_m$ roughly follow the $S_8={\sigma }_8({\mathrm{\Omega }}_m/0.3{)}^{0.5}$ relation. In turn, $S_8$ is highly correlated with the intrinsic galaxy alignment amplitude $A_{\mathrm{IA}}$. For galaxy clustering, the bias $b_g$ is degenerate with both ${\sigma }_8$ and ${\mathrm{\Omega }}_m$, as well as the stochasticity $r_g$. Moreover, the redshift evolution of intrinsic alignment (IA) and bias can cause further parameter confusion. A tomographic two-point probe combination can partially lift these degeneracies. In this work we demonstrate that a deep-learning analysis of combined probes of weak gravitational lensing and galaxy clustering, which we call DeepLSS, can effectively break these degeneracies and yield significantly more precise constraints on ${\sigma }_8$, ${\mathrm{\Omega }}_m$, $A_{\mathrm{IA}}$, $b_g$, $r_g$, and IA redshift evolution parameter ${\eta }_{\mathrm{IA}}$. In a simulated forecast for a stage-III survey, we find that the most significant gains are in the IA sector: the precision of $A_{\mathrm{IA}}$ is increased by approximately 8 times and is almost perfectly decorrelated from $S_8$. Galaxy bias $b_g$ is improved by 1.5 times, stochasticity $r_g$ by 3 times, and the redshift evolution ${\eta }_{\mathrm{IA}}$ and ${\eta }_b$ by 1.6 times. Breaking these degeneracies leads to a significant gain in constraining power for ${\sigma }_8$ and ${\mathrm{\Omega }}_m$, with the figure of merit improved by 15 times. We give an intuitive explanation for the origin of this information gain using sensitivity maps. These results indicate that the fully numerical, map-based forward-modeling approach to cosmological inference with machine learning may play an important role in upcoming large-scale structure surveys. We discuss perspectives and challenges in its practical deployment for a full survey analysis.

• Received 17 March 2022
• Revised 14 June 2022
• Accepted 12 July 2022

DOI:https://doi.org/10.1103/PhysRevX.12.031029

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.

Published by the American Physical Society