Predicted and reported column densities for the data set used in the characterization of the Orion Kleinmann-Low nebula

This dataset contains 172 molecular entries in the chemical inventory of the Orion Kleinmann-Low (Orion KL) used in as the data set used in the work that is currently under review: Scolati et al., "Explaining the Chemical Inventory of Orion KL through Machine Learning", (2023). The dataset was compiled using Herschel spectral line survey as well as ground observations using the IRAM 30 m telescope. The resulting list of molecules were used in the XCLASS fitting program described in Crockett et al. (2014). The full dataset contains 64 unique molecules, including 18 isotoplogues, 9 deuterated, 8 vibrationally excited, and 9 molecules with multiple velocity components. The dataset is structured to provide each molecular entry with their corresponding SMILES string based representation, the beam size, rotational temperature, radial velocity, line width, as well as numerical codes to indicate physical environment within the source (i.e. hot core, compact ridge, etc.), and if the species is vibrationally excited or an isotopologue. The derived column densities reported in Crockett et al. (2014) are provided along with our machine learning model predictions (using the Gradient Boosting Regressor). Finally, a training vs testing tag was added to indicate which entries were split into the training and testing sets.