高压物理学报2026，Vol.40Issue(1)：20-51,32.DOI:10.11858/gywlxb.20251172
机器学习势在材料物性的研究综述
A Review of Machine Learning Potentials in the Study of Materials Properties
摘要
Abstract
With the rapid advancement of artificial intelligence(AI)technologies and hardware capabilities,AI has gradually become a revolutionary tool driving transformative changes across multiple scientific research domains.In the field of materials science,machine learning methods are significant in high-throughput materials design and property prediction.Over the past decade,machine learning-based approaches for constructing interatomic potentials have been widely applied in the study of material properties,and are providing crucial support for the theoretical design of novel materials and in-depth understanding of their underlying microscopic mechanisms.This article reviews the development of machine learning potentials,and introduces their fundamental workflows.The principles of mainstream methods and their applications in materials property research are outlined.Moreover,recent progress in emerging universal potential models is briefly discussed,then concludes with an analysis of current challenges and future research directions.关键词
机器学习势/材料物性/通用势模型Key words
machine learning potential/material properties/universal potential model分类
数理科学引用本文复制引用
LI Jinlong,WANG Hao,GENG Huayun..机器学习势在材料物性的研究综述[J].高压物理学报,2026,40(1):20-51,32.基金项目
国家自然科学基金(12404287) （12404287）
中国工程物理研究院院长基金(YZJJZL2024006) （YZJJZL2024006）
