Work

Phonon dispersion filter: A physics-inspired feature selection for machine learning potentials

Year: 2025

Type: article

Abstract: How to improve the accuracy and precision of machine learning potential functions while reducing their computational cost has long been a subject of considerable interest. In this regard, a common approach is to reduce the number of descriptors through feature selection and dimensionality reduction, thereby improving computational efficiency. In our paper, we propose a descriptor selection method based on the material’s phonon spectrum, which is called a phonon dispersion filter (PDF) method. Compared to other mathematics-based machine learning feature selection methods, the PDF method is a more physics-based feature selection approach. Taking graphene and bulk silicon as examples, we provide a detailed introduction to the screening process of the PDF method and its underlying principles. Furthermore, we test the PDF method on two types of descriptors: Atom-centered symmetry functions descriptors and smooth overlap of atomic positions descriptors. Both demonstrate promising screening results.

Source: Journal of Applied Physics

DOI: 10.1063/5.0253209

Authors: Tianyan Xu, Yixuan Xue, Harold S. Park, Jinwu Jiang

Institutions: Shanghai University, Boston University, Zhejiang Lab

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $3,500

Funder: National Natural Science Foundation of China