From few to many maps: A fast map-level emulator for extreme augmentation of CMB systematics datasets

Abstract

We introduce a novel, fast, and efficient generative model built upon scattering covariances, the most recent iteration of the scattering transforms statistics. This model is designed to augment by several orders of magnitude the number of map simulations in datasets of computationally expensive CMB instrumental systematics simulations, including their non-Gaussian and inhomogeneous features. Unlike conventional neural network-based algorithms, this generative model requires only a minimal number of training samples, making it highly compatible with the computational constraints of typical CMB simulation campaigns. We validate the method using realistic simulations of CMB systematics, which are particularly challenging to emulate, and perform extensive statistical tests to confirm its ability to produce new statistically independent approximate realizations. Remarkably, even when trained on as few as 10 simulations, the emulator closely reproduces key summary statistics -- including the angular power spectrum, scattering coefficients, and Minkowski functionals -- and provides pixel-to-pixel covariance estimates with substantially reduced sample noise compared to those obtained without augmentation. The proposed approach has the potential to shift the paradigm in simulation campaign design. Instead of producing large numbers of low- or medium-accuracy simulations, future pipelines can focus on generating a few high-accuracy simulations that are then efficiently augmented using such generative model. This promises significant benefits for current and forthcoming cosmological surveys such as $Planck$, $LiteBIRD$, Simons Observatory, CMB-S4, Euclid and Rubin-LSST. We make both the general framework for scattering transform statistics available at https://github.com/jmdelouis/HealpixML and the emulator available at https://github.com/pcampeti/CMBSCAT.

Accepted for publication in A&A. Clarified and detailed application to SO pixelization, multiplicative systematics, other instrumental systematics and foregrounds; added details on kernel size effect and role of Minkowski functionals. Codes and examples available at https://github.com/pcampeti/CMBSCAT/ and https://github.com/jmdelouis/HealpixML. 12 pages + appendices, 12 figures

References in corpus (14)

• BICEP / Keck XIII: Improved Constraints on Primordial Gravitational Waves using Planck, WMAP, and BICEP/Keck Observations through the 2018 Observing Season
• Why your model parameter confidences might be too optimistic -- unbiased estimation of the inverse covariance matrix
• Improved limits on the tensor-to-scalar ratio using BICEP and Planck
• Towards an Optimal Estimation of Cosmological Parameters with the Wavelet Scattering Transform
• Precise Cosmological Constraints from BOSS Galaxy Clustering with a Simulation-Based Emulator of the Wavelet Scattering Transform
• Galaxy Clustering Analysis with SimBIG and the Wavelet Scattering Transform
• A new approach for the statistical denoising of Planck interstellar dust polarization data
• Non-Gaussian modelling and statistical denoising of Planck dust polarization full-sky maps using scattering transforms
• Single frequency CMB B-mode inference with realistic foregrounds from a single training image
• Minkowski Functionals of CMB polarisation intensity with Pynkowski: theory and application to Planck and future data
• Scattering Spectra Models for Physics
• Generative models of astrophysical fields with scattering transforms on the sphere
• Generative Models of Multi-channel Data from a Single Example -- Application to Dust Emission
• Inference of the optical depth to reionization $\tau$ from $\text{Planck}$ CMB maps with convolutional neural networks