期刊
ANGEWANDTE CHEMIE-INTERNATIONAL EDITION
卷 61, 期 25, 页码 -出版社
WILEY-V C H VERLAG GMBH
DOI: 10.1002/anie.202204244
关键词
Density Functional Calculations; Machine Learning; Structure Elucidation; Surface Chemistry
资金
- Knut and Alice Wallenberg (KAW) [KAW 2015.0058]
- Swedish Research Council [2018-05374, 349-2011-6491]
- Danish National Research Foundation through the Center of Excellence InterCat [DNRF150]
- VILLUM FONDEN [16562]
- Austrian Science Fund (FWF, SFB Project 'TACO', F81))
- Swedish Research Council [2018-05374] Funding Source: Swedish Research Council
This study demonstrates the use of an evolutionary algorithm and machine learning methods to solve the unknown surface structure of a (4x4) surface oxide on Pt3Sn(111). The algorithm is efficient and robust, providing a broader application in surface studies.
Determination of the atomic structure of solid surfaces typically depends on comparison of measured properties with simulations based on hypothesized structural models. For simple structures, the models may be guessed, but for more complex structures there is a need for reliable theory-based search algorithms. So far, such methods have been limited by the combinatorial complexity and computational expense of sufficiently accurate energy estimation for surfaces. However, the introduction of machine learning methods has the potential to change this radically. Here, we demonstrate how an evolutionary algorithm, utilizing machine learning for accelerated energy estimation and diverse population generation, can be used to solve an unknown surface structure-the (4x4) surface oxide on Pt3Sn(111)-based on limited experimental input. The algorithm is efficient and robust, and should be broadly applicable in surface studies, where it can replace manual, intuition based model generation.
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