Element Code from Pseudopotential as Efficient Descriptors for a Machine Learning Model to Explore Potential Lead-Free Halide Perovskites.

The rapid development of machine learning has proven its potential in material science. To acquire an accurate and promising result, the choice of descriptor plays an essential role in dictating the model performance. In this work, we introduce a set of novel descriptors, Element Code, which is generated from pseudopotential. Using a variational autoencoder to perform unsupervised learning, the produced Element Code is verified to contain representative information on elements. Attributed to the successful extraction of information from pseudopotential, Element Code can serve as the primary descriptor for the machine learning model. We construct a model using Element Code as the sole descriptor to predict the bandgap of a lead-free double halide perovskite, and an accuracy of 0.951 and mean absolute error of 0.266 eV are achieved. We believe our work can offer insights into selecting lead-free halide perovskites and establish a paradigm of exploring new materials.