@article{liu_bordoloi_2021, title={A deep learning approach to quasar continuum prediction}, volume={502}, ISSN={["1365-2966"]}, DOI={10.1093/mnras/stab177}, abstractNote={ABSTRACT
               We present a novel intelligent quasar continuum neural network (iQNet), predicting the intrinsic continuum of any quasar in the rest-frame wavelength range of $1020 \, {\mathring{\rm A}}\le \lambda _{\text{rest}} \le 1600 \, {\mathring{\rm A}}$. We train this network using high-resolution Hubble Space Telescope/Cosmic Origin Spectrograph ultraviolet quasar spectra at low redshift (z ∼ 0.2) from the Hubble Spectroscopic Legacy Archive (HSLA), and apply it to predict quasar continua in different astronomical surveys. We utilize the HSLA quasar spectra that are well defined in the rest-frame wavelength range of [1020, 1600] Å with an overall median signal-to-noise ratio of at least 5. The iQNet model achieves a median absolute fractional flux error of 2.24 per cent on the training quasar spectra, and 4.17 per cent on the testing quasar spectra. We apply iQNet and predict the continua of ∼3200 Sloan Digital Sky Survey Data Release 16 quasar spectra at higher redshift (2 < z ≤ 5) and measure the redshift evolution of mean transmitted flux (〈F〉) in the Ly α forest region. We measure a gradual evolution of 〈F〉 with redshift, which we characterize as a power-law fit to the effective optical depth of the Ly α forest. Our measurements are broadly consistent with other estimates of 〈F〉 in the literature but provide a more accurate measurement as we are directly measuring the quasar continuum where there is minimum contamination from the Ly α forest. This work proves that the deep learning iQNet model can predict the quasar continuum with high accuracy and shows the viability of such methods for quasar continuum prediction.}, number={3}, journal={MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY}, author={Liu, Bin and Bordoloi, Rongmon}, year={2021}, month={Apr}, pages={3510–3532} }