HyPhy: Deep Generative Conditional Posterior Mapping of Hydrodynamical Physics

Abstract

Generating large volume hydrodynamical simulations for cosmological observables is a computationally demanding task necessary for next generation observations. In this work, we construct a novel fully convolutional variational auto-encoder (VAE) to synthesize hydrodynamic fields conditioned on dark matter fields from N-body simulations. After training the model on a single hydrodynamical simulation, we are able to probabilistically map new dark matter only simulations to corresponding full hydrodynamical outputs. By sampling over the latent space of our VAE, we can generate posterior samples and study the variance of the mapping. We find that our reconstructed field provides an accurate representation of the target hydrodynamical fields as well as a reasonable variance estimates. This approach has promise for the rapid generation of mocks as well as for implementation in a full Bayesian inverse model of observed data.

13 pages, 11 figures

References in corpus (6)

• Data Augmentation Using GANs
• HIGAN: Cosmic Neutral Hydrogen with Generative Adversarial Networks
• Simulating intergalactic gas for DESI-like small scale Lymanα forest observations
• Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability
• Effect of the Metallicity on the X-ray Emission from the Warm-Hot Intergalactic Medium
• Fast, high-fidelity Lyman $\alpha$ forests with convolutional neural networks

Cited by in corpus (8)

• The CAMELS project: public data release
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• MAHGIC: A Model Adapter for the Halo-Galaxy Inter-Connection
• Differentiable Cosmological Hydrodynamics for Field-Level Inference and High Dimensional Parameter Constraints
• TensorFlow Hydrodynamics Analysis for Ly-$\alpha$ Simulations
• Modeling the Cosmological Lyman-$\alpha$ Forest at the Field Level
• Differentiable Fuzzy Cosmic-Web for Field Level Inference
• Bridging Simulations and EFT: A Hybrid Model of the Lyman-Alpha Forest Field