期刊
SCIENCE ADVANCES
卷 3, 期 12, 页码 -出版社
AMER ASSOC ADVANCEMENT SCIENCE
DOI: 10.1126/sciadv.1701816
关键词
-
资金
- Leverhulme Early Career Fellowship
- Isaac Newton Trust
- Collaborative Computational Project for NMR Crystallography (CCP-NC) - Engineering and Physical Sciences Research Council (EPSRC) [EP/M022501/1]
- National Center of Competence in Research MARVEL - Swiss National Science Foundation
- European Research Council under the European Union's Horizon research and innovation programme [677013-HBMAP]
- European Union grant NOMAD [676580]
- EPSRC [EP/L014742/1, EP/P002188/1, EP/J010847/1, EP/J022012/1]
- Office of Naval Research through the U.S. Naval Research Laboratory's core basic research program
- Argonne Leadership Computing Facility [DE-AC02-06CH11357]
- ARCHER under the UKCP EPSRC [EP/K013564/1, EP/P022561/1]
- Engineering and Physical Sciences Research Council [EP/P022596/1, EP/K014560/1, EP/J022012/1] Funding Source: researchfish
- EPSRC [EP/J022012/1, EP/P022596/1, EP/M022501/1, EP/J010847/1, EP/P002188/1, EP/K013564/1, EP/L027682/1, EP/K014560/1] Funding Source: UKRI
Determining the stability ofmolecules and condensed phases is the cornerstone of atomisticmodeling, underpinning our understanding of chemical andmaterials properties and transformations. We show that amachine-learningmodel, based on a local description of chemical environments and Bayesian statistical learning, provides a unified framework to predict atomic-scale properties. It captures the quantum mechanical effects governing the complex surface reconstructions of silicon, predicts the stability of different classes of molecules with chemical accuracy, and distinguishes active and inactive protein ligands with more than 99% reliability. The universality and the systematic nature of our framework provide new insight into the potential energy surface of materials and molecules.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据