We trained two models for saturation vapor pressure estimation on experimental data. The adGC2NN-broad is a general model with broad scope that is suitable for both organic and inorganic molecules and achieves a mean absolute error (MAE) of 0.67 log-units (R2 = 0.86) on the training data.
The adGC2NN-confined model is specialized on organic compounds with functional groups often encountered in atmospheric SOA, achieving an even stronger correlation with independent test data (MAE = 0.36 log-units, R2 = 0.97).
The models use molecular descriptors like molar mass alongside molecular graphs containing atom and bond features as representations of molecular structure. In adaptive-depth GC2NN, the number of evaluated graph layers depends on molecular size. The most suitable model is automatically selected for each compound.
Krüger et al., Geosci. Model Dev. 18, 7357–7371, 2025