Fig. 2: Benchmark of the short-range and long-range models on bulk and interfacial electrolytes.
From: Machine learning of charges and long-range interactions from energies and forces
a A bulk electrolyte configuration (upper panel) and an electrolyte-vapor configuration (lower panel) of KF in water electrolyte of 1 KF ion pair and 233 water molecules, randomly selected from the training set. b Comparison of the true and the predicted charges for the Cartesian atomic cluster expansion (CACE) long-range (CACE-LR) models with a cutoff radius rcut of 4.5 Å and trained on N configurations. c The mean absolute errors (MAEs) on forces (F), and charges for short-range (SR) and long-range (LR) models trained using different N numbers of samples. The MP1 indicates models using one message-passing layer.
