New measurements of the Lyman-α forest continuum and effective optical depth with LyCAN and DESI Y1 data

We present the Lyman-α Continuum Analysis Network (LyCAN), a Convolutional Neural Network that predicts the unabsorbed quasar continuum within the rest-frame wavelength range of 1040-1600 Angstroms based on the red side of the Lyman-α emission line (1216-1600 Angstroms). We developed synthetic spectra based on a Gaussian Mixture Model representation of Nonnegative Matrix Factorization (NMF) coefficients. These coefficients were derived from high-resolution, low-redshift (z<0.2) Hubble Space Telescope/Cosmic Origins Spectrograph quasar spectra. We supplemented this COS-based synthetic sample with an equal number of DESI Year 5 mock spectra. LyCAN performs extremely well on testing sets, achieving a median error in the forest region of 1.5 sample, and 4.1 Component Analysis (PCA)- and NMF-based prediction methods using the same training set by a factor of two or more. We predict the intrinsic continua of 83,635 DESI Year 1 spectra in the redshift range of 2.1 ≤ z ≤ 4.2 and perform an absolute measurement of the evolution of the effective optical depth. This is the largest sample employed to measure the optical depth evolution to date. We fit a power-law of the form τ(z) = τ_0 (1+z)^γ to our measurements and find τ_0 = (2.46 ± 0.14)×10^-3 and γ = 3.62 ± 0.04. Our results show particular agreement with high-resolution, ground-based observations around z = 2, indicating that LyCAN is able to predict the quasar continuum in the forest region with only spectral information outside the forest.