Predicting Crystal Structures with Data Mining of Quantum Calculations

TL;DR

This paper introduces a data mining approach using quantum calculations to predict crystal structures, aiming to improve upon traditional quantum and empirical methods in materials research.

Contribution

It develops a novel tool that extracts heuristic rules from extensive ab-initio calculations for crystal structure prediction.

Findings

Successfully demonstrates rule extraction from quantum data

Provides a new predictive tool for crystal structures

Enhances prediction accuracy over empirical methods

Abstract

Predicting and characterizing the crystal structure of materials is a key problem in materials research and development. It is typically addressed with highly accurate quantum mechanical computations on a small set of candidate structures, or with empirical rules that have been extracted from a large amount of experimental information, but have limited predictive power. In this letter, we transfer the concept of heuristic rule extraction to a large library of ab-initio calculated information, and demonstrate that this can be developed into a tool for crystal structure prediction.