Crystal structure prediction with machine learning-based element substitution
This work addresses the challenge of crystal structure prediction in solid-state physics, offering a more efficient alternative to traditional methods for complex systems, though it appears incremental as it builds on existing database and substitution techniques.
The authors tackled the problem of predicting stable crystal structures for given chemical compositions by developing a machine learning-based element substitution method, achieving 96.4% accuracy in determining crystal structure isomorphism without relying on expensive first-principles calculations.
The prediction of energetically stable crystal structures formed by a given chemical composition is a central problem in solid-state physics. In principle, the crystalline state of assembled atoms can be determined by optimizing the energy surface, which in turn can be evaluated using first-principles calculations. However, performing the iterative gradient descent on the potential energy surface using first-principles calculations is prohibitively expensive for complex systems, such as those with many atoms per unit cell. Here, we present a unique methodology for crystal structure prediction (CSP) that relies on a machine learning algorithm called metric learning. It is shown that a binary classifier, trained on a large number of already identified crystal structures, can determine the isomorphism of crystal structures formed by two given chemical compositions with an accuracy of approximately 96.4\%. For a given query composition with an unknown crystal structure, the model is used to automatically select from a crystal structure database a set of template crystals with nearly identical stable structures to which element substitution is to be applied. Apart from the local relaxation calculation of the identified templates, the proposed method does not use ab initio calculations. The potential of this substation-based CSP is demonstrated for a wide variety of crystal systems.