Anomaly-Detection-Driven Screening of Thermodynamic Stability from Composition Descriptors Alone.

ABSTRACT: Materials informatics tends to rely on existing structural database searches that constrain exploration by omitting unregistered compositions. In this study, an autoencoder-based anomaly detector was developed using composition-only descriptors as input features. The model was trained on thermodynamically stable phases─defined as those on the convex hull with an energy above hull (ΔE_hull) of 0 eV/atom─as well as nearly stable phases with ΔE_hull < 0.01 eV/atom, sourced from the Materials Project inorganic database. The reconstruction error (RMSE) was used as the anomaly score. It was shown that the RMSE increased systematically with apparent thermal destabilization─that is, increasing energy above hull. It was also shown that for 50,000 dumm

SUBMITTER: Makino K 

PROVIDER: S-EPMC12927008 | biostudies-literature | 2026 Feb

REPOSITORIES: biostudies-literature