Explaining dark matter halo density profiles with neural networks

L Lucie-Smith, HV Peiris, A Pontzen - Physical Review Letters, 2024 - APS
We use explainable neural networks to connect the evolutionary history of dark matter halos
with their density profiles. The network captures independent factors of variation in the …

Hybrid bias and displacement emulators for field-level modelling of galaxy clustering in real and redshift space

M Pellejero Ibañez, RE Angulo… - Monthly Notices of the …, 2024 - academic.oup.com
Recently, hybrid bias expansions have emerged as a powerful approach to modelling the
way in which galaxies are distributed in the Universe. Similarly, field-level emulators have …

AI-assisted super-resolution cosmological simulations III: time evolution

X Zhang, P Lachance, Y Ni, Y Li… - Monthly Notices of …, 2024 - academic.oup.com
In this work, we extend our recently developed super-resolution (SR) model for cosmological
simulations to produce fully time-consistent evolving representations of the particle phase …

Can denoising diffusion probabilistic models generate realistic astrophysical fields?

N Mudur, DP Finkbeiner - arxiv preprint arxiv:2211.12444, 2022 - arxiv.org
Score-based generative models have emerged as alternatives to generative adversarial
networks (GANs) and normalizing flows for tasks involving learning and sampling from …