The central role of density functional theory in the AI age

• 成果类型: Review
• 署名作者: Huang, Bing; von Rudorff, Guido Falk; von Lilienfeld, O. Anatole
• 署名单位: University of Vienna; Universitat Kassel; Vector Institute for Artificial Intelligence; University of Toronto; University of Toronto; University of Toronto; Technical University of Berlin
• 刊物名称: SCIENCE
• ISSN/ISSBN: 0036-9457
• DOI: 10.1126/science.abn3445
• 发表日期: 2023-07-14
• 页码: 170-175
• 关键词: machine learning-models; nearsightedness; frontiers; matrix; robot

摘要

Density functional theory (DFT) plays a pivotal role in chemical and materials science because of its relatively high predictive power, applicability, versatility, and computational efficiency. We review recent progress in machine learning (ML) model developments, which have relied heavily on DFT for synthetic data generation and for the design of model architectures. The general relevance of these developments is placed in a broader context for chemical and materials sciences. DFT-based ML models have reached high efficiency, accuracy, scalability, and transferability and pave the way to the routine use of successful experimental planning software within self-driving laboratories.