3D ScatterNet: Inference from 21 cm Light-cones
arXiv:2307.09530
Abstract
The Square Kilometre Array (SKA) will have the sensitivity to take the 3D light-cones of the 21 cm signal from the epoch of reionization. This signal, however, is highly non-Gaussian and can not be fully interpreted by the traditional statistic using power spectrum. In this work, we introduce the 3D ScatterNet that combines the normalizing flows with solid harmonic wavelet scattering transform, a 3D CNN featurizer with inductive bias, to perform implicit likelihood inference (ILI) from 21 cm light-cones. We show that 3D ScatterNet outperforms the ILI with a fine-tuned 3D CNN in the literature. It also reaches better performance than ILI with the power spectrum for varied light-cone effects and varied signal contaminations.
9 pages, 4 figures, 2 tables. Accepted to ICML 2023 Machine Learning for Astrophysics workshop. Comments and suggestions are welcome
References in corpus (6)
- Efficient Simulations of Early Structure Formation and Reionization
- Fast likelihood-free cosmology with neural density estimators and active learning
- Wavelet Moments for Cosmological Parameter Estimation
- Inferring Astrophysics and Dark Matter Properties from 21cm Tomography using Deep Learning
- Exploration of 3D wavelet scattering transform coefficients for line-intensity mapping measurements
- Learnable wavelet neural networks for cosmological inference