babylonpolice.com

arXiv:2403.18458v1 Announce Type: new
Abstract: We present the results of a machine learning study to measure the dust content of galaxies observed with JWST at z > 6 through the use of trained neural networks based on high-resolution IllustrisTNG simulations. Dust is an important unknown in the evolution and observability of distant galaxies and is degenerate with other stellar population features through spectral energy fitting. As such, we develop and test a new SED-independent machine learning method to predict dust attenuation and sSFR of high redshift (z > 6) galaxies. Simulated galaxies were constructed using the IllustrisTNG model, with a variety of dust contents parameterized by E(B-V) and A(V) values, then used to train Convolutional Neural Network (CNN) models using supervised learning through a regression model. We demonstrate that within the context of these simulations, our single and multi-band models are able to predict dust content of distant galaxies to within a 1$\sigma$ dispersion of A(V) $\sim 0.1$. Applied to spectroscopically confirmed z > 6 galaxies from the JADES and CEERS programs, our models predicted attenuation values of A(V) < 0.7 for all systems, with a low average (A(V) = 0.28). Our CNN predictions show larger dust attenuation but lower amounts of star formation compared to SED fitted values. Both results show that distant galaxies with confirmed spectroscopy are not extremely dusty, although this sample is potentially significantly biased. We discuss these issues and present ideas on how to accurately measure dust features at the highest redshifts using a combination of machine learning and SED fitting.