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

By Runhai Ouyang, Stefano Curtarolo, Emre Ahmetcik, Matthias Scheffler, Luca M. Ghiringhelli. PHYSICAL REVIEW MATERIALS, 2017

557 citations recorded by the source corpus.

The lack of reliable methods for identifying descriptors---the sets of parameters capturing the underlying mechanisms of a material's 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. The sure independence screening and sparsifying operator (SISSO) 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 is tested beyond the training data: It rediscovers the available pressure-induced insulator-to-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.

Subfields: Atomic and Molecular Physics, and Optics, Inorganic Chemistry, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/1cde9d6b69431b530ce47bc486e1d842ff85ea3f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Inorganic Chemistry

Matthias Scheffler

In Materials Chemistry

Citations in the corpus

Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel (2019, background): “Recently, SISSO (Sure Independence Screening and Sparsifying Operator) approach has been developed [39], which can reduce immense features spaces to lowdimensional spaces based on compressed-sensing, to predict target property of material using various physical descriptors.”
New tolerance factor to predict the stability of perovskite oxides and halides (2018, methodology): “by 5, τ remains the highest performing descriptor (classification accuracy of 92% on the 576 compound set). An important distinction between the SISSO approach described here and by Ouyang et al. in (32) is the choice of sparsifying operator (SO). In this work, domain overlap is used to rank the fea”