arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.04045cond-mat.mtrl-scics.LGphysics.comp-ph
收藏

一台实验驱动的自动机器学习难熔氧化物的原子间势

An Experimentally Driven Automated Machine Learned lnter-Atomic Potential for a Refractory Oxide

Argonne National Laboratory(阿贡国家实验室);Helmholtz-Institute Munster(明斯特亥姆霍兹研究所);Forschungszentrum Julich GmbH(于利希研究中心);University of Cambridge(剑桥大学)

Ganesh Sivaraman, Leighanne Gallington, Anand Narayanan Krishnamoorthy, Marius Stan, Gabor Csanyi, Alvaro Vazquez-Mayagoitia, Chris J. Benmore

摘要:

了解难熔氧化物的结构和性能对于高温应用至关重要。在这项工作中,结合实验和仿真方法使用自动闭环通过主动学习,这是由X射线和中子衍射测量初始化,并依次改善机器学习模型,直到实验预定的相空间被覆盖。一个多相电位产生的典型例子的原型耐火氧化物,HfO 2,通过绘制最小数量的训练配置从室温到液态在~ 2900 ℃。该方法大大减少了模型开发时间和人力。

英文摘要:

Understanding the structure and properties of refractory oxides are critical for high temperature applications. In this work, a combined experimental and simulation approach uses an automated closed loop via an active-learner, which is initialized by X-ray and neutron diffraction measurements, and sequentially improves a machine-learning model until the experimentally predetermined phase space is covered. A multi-phase potential is generated for a canonical example of the archetypal refractory oxide, HfO2, by drawing a minimum number of training configurations from room temperature to the liquid state at ~2900oC. The method significantly reduces model development time and human effort.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑