SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates

TL;DR

SISSO is a novel compressed-sensing method that efficiently identifies low-dimensional descriptors for materials properties, enabling accurate predictions even with small datasets and uncovering new insights for materials development.

Contribution

The paper introduces SISSO, a systematic compressed-sensing approach for discovering optimal descriptors in materials science, handling large feature spaces and small training sets.

Findings

Successfully predicts ground-state enthalpies of binary materials.

Accurately classifies metals and insulators in binary compounds.

Discovers pressure-induced insulator-metal transitions and predicts new candidates.

Abstract

The lack of reliable methods for identifying descriptors - the sets of parameters capturing the underlying mechanisms of a materials property - is one of the key factors hindering efficient materials development. Here, we propose a systematic approach for discovering descriptors for materials properties, within the framework of compressed-sensing based dimensionality reduction. SISSO (sure independence screening and sparsifying operator) tackles immense and correlated features spaces, and converges to the optimal solution from a combination of features relevant to the materials' property of interest. In addition, SISSO gives stable results also with small training sets. The methodology is benchmarked with the quantitative prediction of the ground-state enthalpies of octet binary materials (using ab initio data) and applied to the showcase example of predicting the metal/insulator classification of binaries (with experimental data). Accurate, predictive models are found in both cases. For the metal-insulator classification model, the predictive capability are tested beyond the training data: It rediscovers the available pressure-induced insulator->metal transitions and it allows for the prediction of yet unknown transition candidates, ripe for experimental validation. As a step forward with respect to previous model-identification methods, SISSO can become an effective tool for automatic materials development.