Investigation of phase transition, mechanical behavior and lattice thermal conductivity of halogen perovskites using machine learning interatomic potentials.

Using a machine learning (ML) approach to fit DFT data, interatomic potentials have been successfully extracted. In this study, the phase transition, mechanical behavior and lattice thermal conductivity are investigated for halogen perovskites using NEP-based MD simulations in a large supercell including 16 000 atoms, which breaks through the size and temperature effects in DFT. A clear phase transition from orthorhombic (γ) → tetragonal (ß) → cubic (α) is observed during the heating process. During the cooling process, CsPbCl3 and CsPbBr3 exhibit perfect reversible behavior, while CsPbI3 only undergoes a phase transition from α to ß. Then, the key mechanical parameters, including Poisson's ratio, tensile strength, critical strain and bulk modulus, are predicted. The thermal conductivity is also investigated using the NEP-based MD simulations. At room temperature, they exhibit extremely low thermal conductivity. The predicted results are compared with the experimental results, and the rationality of ML potentials has been confirmed.