Machine learning oxygen vacancy formation energies in perovskites published in J. Am. Chem. Soc.

16 Aug 2021

Recent work on the building a robust and physically-intuitive machine learning model on predicting oxygen vacancy formation energies in ternary oxide perovskites was published today in Journal of American Chemical Society. The model uses metrics such as solid-state reduction potentials, crystal bond dissociation energies, energy above the convex hull, and the band gap at Gamma point, thus allowing for equivalent models to be built with either experimental or theoretical data or both. The paper was written by Dr. Robert Wexler (Princeton University), Dr. Sai Gautam Gopalakrishnan, Dr. Ellen Stechel (Arizona State University) and Prof. Emily A. Carter (University of California Los Angeles).

© Sai Gautam Gopalakrishnan - Powered by Jekyll and adapted from, with inputs from PC.