SPT-NRTL: A physics-guided machine learning model to predict thermodynamically consistent activity coefficients

The data repository contains the following: Database of 100 Mio. sets of NRTL Parameters predicted using SPT-NRTL Jupyter notebook to get the corresponding NRTL parameters for given SMILES code combination Lookup table to match the SMILES codes with the corresponding hashs used for the file names The work is part of the following publication: https://doi.org/10.1016/j.fluid.2023.113731