Learning physical descriptors for materials science by compressed sensing

TL;DR

This paper introduces a compressed sensing methodology for feature selection in materials science, enabling the discovery of physical descriptors that quantitatively relate material properties to their structure.

Contribution

It presents a novel application of compressed sensing for identifying physical descriptors and equations in materials data, advancing data-driven materials modeling.

Findings

Successfully built a model predicting crystal structures of binary semiconductors.

Demonstrated the effectiveness of compressed sensing in feature selection for materials science.

Provided a proof of concept for quantitative property prediction using physical descriptors.

Abstract

The availability of big data in materials science offers new routes for analyzing materials properties and functions and achieving scientific understanding. Finding structure in these data that is not directly visible by standard tools and exploitation of the scientific information requires new and dedicated methodology based on approaches from statistical learning, compressed sensing, and other recent methods from applied mathematics, computer science, statistics, signal processing, and information science. In this paper, we explain and demonstrate a compressed-sensing based methodology for feature selection, specifically for discovering physical descriptors, i.e., physical parameters that describe the material and its properties of interest, and associated equations that explicitly and quantitatively describe those relevant properties. As showcase application and proof of concept, we describe how to build a physical model for the quantitative prediction of the crystal structure of binary compound semiconductors.