A fast machine learning tool to predict the composition of astronomical ices from infrared absorption spectra

Abstract

Current observations taken by James Webb Space Telescope (JWST) allow us to observe the absorption features of icy mantles that cover interstellar dust grains, which are mainly composed of ${\mathrm{H}}_2\mathrm{O}$, $\mathrm{CO}$, and $\mathrm{C}{\mathrm{O}}_2$, along with other minor species. Thanks to its sensitivity and spectral resolution, JWST has the potential to observe ice features towards hundreds of sources at different stages along the process of star formation. However, identifying the spectral features of the different species and quantifying the ice composition is not trivial and requires complex spectroscopic analysis. We present Automatic Ice Composition Estimator (AICE), a new tool based on artificial neural networks. Based on the infrared (IR) ice absorption spectrum between 2.5 and 10 microns, AICE predicts the ice fractional composition in terms of ${\mathrm{H}}_2\mathrm{O}$, $\mathrm{CO}$, $\mathrm{C}{\mathrm{O}}_2$, $\mathrm{C}{\mathrm{H}}_3\mathrm{OH}$, $\mathrm{N}{\mathrm{H}}_3$, and $\mathrm{C}{\mathrm{H}}_4$. To train the model, we used hundreds of laboratory experiments of ice mixtures from different databases, which were reprocessed with baseline subtraction and normalisation. Once trained, AICE takes less than one second on a conventional computer to predict the ice composition associated with the observed IR absorption spectrum, with typical errors of $\sim$3 $\%$ in the species fraction. We tested its performance on two spectra reported towards the NIR38 and J110621 background stars observed within the JWST Ice Age program, demonstrating a good agreement with previous estimations of the ice composition. The fast and accurate performance of AICE enables the systematic analysis of hundreds of different ice spectra with a modest time investment. In addition, this model can be enhanced and re-trained with more laboratory data, improving the precision of the predictions and expanding the list of predicted species.

24 pages, 20 figures

References in corpus (28)

• Infrared Emission from Interstellar Dust. IV. The Silicate-Graphite-PAH Model in the Post-Spitzer Era
• Observations of the Icy Universe
• Dense Cores in Dark Clouds. XIV. N2H+(1-0) maps of dense cloud cores
• An Ice Age JWST inventory of dense molecular cloud ices
• A 3-5 micron VLT spectroscopic survey of embedded young low mass stars I: Structure of the CO ice
• Photoprocesses in protoplanetary disks
• Experimental evidence for water formation on interstellar dust grains by hydrogen and oxygen atoms
• Ice and Dust in the Quiescent Medium of Isolated Dense Cores
• A 3-5$\mu$m VLT spectroscopic survey of embedded young low mass stars II; OCN${}^{-}$
• CORINOS I: JWST/MIRI Spectroscopy and Imaging of a Class 0 protostar IRAS 15398-3359
• Effects of CO2 on H2O band profiles and band strengths in mixed H2O:CO2 ices
• An experimental study of the surface formation of methane in interstellar molecular clouds
• High Resolution 4.7 um Keck/NIRSPEC Spectra of Protostars. II: Detection of the 13CO Isotope in Icy Grain Mantles
• Infrared spectroscopy of solid CO-CO2 mixtures and layers
• Changes in the morphology of interstellar ice analogues after hydrogen atom exposure
• Infrared Spectroscopic Survey of the Quiescent Medium of Nearby Clouds: I. Ice Formation and Grain Growth in Lupus
• Infrared spectroscopy of HCOOH in interstellar ice analogues
• LIDA - The Leiden Ice Database for Astrochemistry
• A survey of H${}_2$O, CO${}_2$ and CO ice features towards background stars and low mass YSOs using AKARI
• Influence of grain growth on CO2 ice spectroscopic profiles : Modelling for dense cores and disks
• Ammonia snow-lines and ammonium salts desorption
• JWST observations of ${}^{13}$CO${}_2$ ice: Tracing the chemical environment and thermal history of ices in protostellar envelopes
• The complex organic molecular content in the L1517B starless core
• Entrapment of CO in CO2 ice
• Influence of the ice structure on the soft UV photochemistry of PAHs embedded in solid water
• Fitting infrared ice spectra with genetic modelling algorithms. Presenting the ENIIGMA fitting tool
• Water and Methanol Ice in L1544
• Nitrogen fractionation in ammonia and its insights on nitrogen chemistry

Cited by in corpus (1)

• Optical constants of Ih, Ic, and amorphous H${}_2$O ices in the THz and IR ranges