Search for: All records

ABSTRACT We present a coherent, re-usable python framework building on the CosmoPower emulator code for high-accuracy calculations of cosmological observables with Einstein–Boltzmann codes. For detailed statistical analyses, such codes require high computing power, making parameter space exploration costly, especially for beyond-$$\Lambda$$CDM analyses. Machine learning-enabled emulators of Einstein–Boltzmann codes are becoming an increasingly popular solution to this problem. To enable generation, sharing, and use of emulators for inference, we define standards for robustly describing, packaging, and distributing them. We present software for easily performing these tasks in an automated and replicable manner and provide examples and guidelines for generating emulators and wrappers for using them in popular cosmological inference codes. We demonstrate our framework with a suite of high-accuracy emulators for the CAMB code’s calculations of CMB $$C_\ell$$, $P(k)$, background evolution, and derived parameter quantities. We show these emulators are accurate enough for analysing both $$\Lambda$$CDM and a set of extension models ($$N_{\rm eff}$$, $$\sum m_\nu$$, $$w_0 w_a$$) with stage-IV observatories, recovering the original high-accuracy spectra to tolerances well within the cosmic variance uncertainties. We show our emulators also recover cosmological parameters in a simulated cosmic-variance limited experiment, finding results well within $$0.1 \sigma$$ of the input cosmology, while requiring $$\lesssim 1/50$$ of the evaluation time.