Detecting neutral hydrogen at z greater than or similar to 3 in large spectroscopic surveys of quasars

We present a pipeline based on a random forest classifier for the identification of high column density clouds of neutral hydrogen (i.e. the Lyman limit systems, LLSs) in absorption within large spectroscopic surveys of z greater than or similar to 3 quasars. We test the performance of this method on mock quasar spectra that reproduce the expected data quality of the Dark Energy Spectroscopic Instrument and the WHT (William Herschel Telescope) Enhanced Area Velocity Explorer surveys, finding greater than or similar to 90 per cent completeness and purity for N-HI greater than or similar to 10(17.2) cm(-2) LLSs against quasars of g < 23 mag at z approximate to 3.5-3.7. After training and applying our method on 10 000 quasar spectra at z approximate to 3.5-4.0 from the Sloan Digital Sky Survey (Data Release 16), we identify approximate to 6600 LLSs with N-HI greater than or similar to 10(17.5) cm(-2) between z approximate to 3.1 and 4.0 with a completeness and purity of greater than or similar to 90 per cent for the classification of LLSs. Using this sample, we measure a number of LLSs per unit redshift of l(z) = 2.32 +/- 0.08 at z = [3.3, 3.6]. We also present results on the performance of random forest for the measurement of the LLS redshifts and HI column densities, and for the identification of broad absorption line quasars.