CsSn(Cl/Br/I)3 Perovskite Alloy DFT Dataset for Machine Learning

This upload contains density functional theory (DFT) calculations of CsSn(Cl/Br/I)3 perovskite alloy. The calculations were performed for a study, where the DFT data was used to train an energy predicting machine learning model for CsSn(Cl/Br/I)3. The code related to the study is available through GitLab (https://gitlab.com/cest-group/learnsolar-cssnclbri).

The data is divided into four data sets. For each set, the atomic structure data with total energies and forces has been separated into an ASE (Atomic Simulation Environment) extended XYZ file. Additional information on the atomic structures (e.g. space groups) is provided in JSON format. The data sets are:

sp_train_setSingle point DFT calculations of 16 000 algorithmically generated CsSn(Cl/Br/I)3 structures of four different space groups: Pm-3m, P4/mbm, I4/mcm, and Pnma. Lattice parameters and atomic positions are determined through Vegard's law, but random deviations have been added to the atom positions, tilting angles of the Sn coordination octahedra, cell volume, cell height-to-width ratio, and some lattice vector angles. Cl/Br/I configurations are randomized. This data set was used to fit an initial machine learning model. The atomic structures included were selected using a clustering algorithm to accelerate learning.

sp_test_setSingle point DFT calculations of 2 600 atomic structures similar to sp_train_set. The Cl/Br/I compositions are uniformly represented, having two atomic structures per composition and space group. This data was used for testing the machine learning model. 

al_dataDFT relaxation structure snapshots from the active learning run that was performed to improve the machine learning model's structure relaxation accuracy. There are 4230 structure snapshots in total.

relax_test_set100 DFT relaxations used for testing the machine learning relaxation accuracy. There are 2881 structure snapshots in total. Both initial (relax_test_set_initial.xyz) and final (relax_test_set_relaxed.xyz) atomic geometries are included.