Pattern Learning Electronic Density of States

TL;DR

This paper introduces a rapid pattern learning approach using principal component analysis to predict electronic density of states in alloys, significantly reducing computational costs while maintaining high accuracy.

Contribution

The method achieves O(1) scaling for DOS prediction, offering a fast alternative to traditional DFT calculations with high pattern similarity.

Findings

Pattern similarity of 91-98% with DFT results

Scales independently of system size, O(1)

Applicable to bulk and surface alloy structures

Abstract

Electronic density of states (DOS) is a key factor in condensed matter physics and material science that determines the properties of metals. First-principles density-functional theory (DFT) calculations have typically been used to obtain the DOS despite the considerable computation cost. Herein, we report a fast pattern learning method for predicting the DOS patterns of not only bulk structures but also surface structures in multi-component alloy systems by a principal component analysis. Within this framework, we use only four features to define the composition, atomic structure, and surfaces of alloys, which are the d-orbital occupation ratio, coordination number, mixing factor, and the inverse of miller indices. While the DFT method scales as O(N^3) in which N is the number of electrons in the system size, our pattern learning method can scale as O(1) regardless of N. Furthermore, our method provides a pattern similarity of 91~98% compared to DFT calculations. This reveals that our learning method will be an alternative that can break the trade-off relationship between accuracy and speed that is well known in the field of electronic structure calculations.