Deep Forest: Neural Network reconstruction of the Lyman-alpha forest

TL;DR

This paper demonstrates that deep learning can effectively reconstruct the optical depth of the Lyman-alpha forest from noisy transmitted flux data, outperforming traditional methods and showing potential for broader cosmological applications.

Contribution

The study introduces a neural network approach for reconstructing Lyman-alpha forest optical depth, surpassing existing methods in accuracy and robustness, and highlights its potential for extension to other cosmological inverse problems.

Findings

Neural network reduces root mean square error by about 50% compared to traditional methods.

Performance gain is consistent across different noise levels, especially in high optical depth regions.

Deep learning approach can be generalized to other physical quantities in cosmology.

Abstract

We explore the use of Deep Learning to infer physical quantities from the observable transmitted flux in the Lyman-alpha forest. We train a Neural Network using redshift z=3 outputs from cosmological hydrodynamic simulations and mock datasets constructed from them. We evaluate how well the trained network is able to reconstruct the optical depth for Lyman-alpha forest absorption from noisy and often saturated transmitted flux data. The Neural Network outperforms an alternative reconstruction method involving log inversion and spline interpolation by approximately a factor of 2 in the optical depth root mean square error. We find no significant dependence in the improvement on input data signal to noise, although the gain is greatest in high optical depth regions. The Lyman-alpha forest optical depth studied here serves as a simple, one dimensional, example but the use of Deep Learning and simulations to approach the inverse problem in cosmology could be extended to other physical quantities and higher dimensional data.