FLAME: Fitting Ly{α} Absorption lines using Machine learning

We introduce FLAME, a machine learning algorithm designed to fit Voigt profiles to HI Lyman-alpha (Lyα) absorption lines using deep convolutional neural networks. FLAME integrates two algorithms: the first determines the number of components required to fit Lyα absorption lines, and the second calculates the Doppler parameter b, the HI column density NHI, and the velocity separation of individual components. For the current version of FLAME, we trained it on low-redshift Lyα forests observed with the Far Ultraviolet gratings of the Cosmic Origin Spectrograph (COS) aboard the Hubble Space Telescope (HST). Drawing on this data, we trained FLAME on ~ 10⁶ simulated Voigt profiles, forward-modeled to Lyα absorption lines observed with HST-COS, to classify lines as either single or double components and then determine Voigt profile fitting parameters. FLAME shows impressive accuracy on the simulated data by identifying more than 98% (90%) of single (double) component lines. It determines b values within ≈ ±8~(15) km s⁻¹ and log NHI/ cm² values within ≈ ± 0.3~(0.8) for 90% of the single (double) component lines. However, when applied to real data, FLAME's component classification accuracy drops by ~ 10%. Despite this, there is a reasonable agreement between the b and NHI distributions obtained from traditional Voigt profile fitting methods and FLAME's predictions. Our mock HST-COS data analysis, designed to emulate real data parameters, demonstrated that FLAME could achieve consistent accuracy comparable to its performance with simulated data. This finding suggests that the drop in FLAME's accuracy when used on real data primarily arises from the difficulty of replicating the full complexity of real data in the training sample.