Defected phosphorene dataset and trained HNNP models

The dataset contains pristine monolayer phosphorene as well as structures with monovacancies and divacancies. The data was obtained using Density Functional Theory (VASP). The Perdew-Burke-Ernzerhof PBE functional was employed with an energy cutoff of 600 eV. The Brillouin zone was sampled by using a 3 × 3 × 1 Gamma-centered mesh. The input.data file is suitable for packages such as n2p2 and Runner. Information about neural network potential are provided in the publication (10.1021/acs.jpcc.3c05713).