Expanding Materials Selection Via Transfer Learning for High-Temperature Oxide Selection

Expanding Materials Selection Via Transfer Learning for High-Temperature Oxide Selection
复制标题

通过高温氧化物选择的迁移学习扩大材料选择

DOI:
10.1007/s11837-020-04411-1
复制
发表时间:
2021
期刊:
JOM
影响因子:
2.6
通讯作者:
Strachan, Alejandro
Strachan, Alejandro
中科院分区:
材料科学3区
文献类型:
--
作者:
McClure, Zachary D.;Strachan, Alejandro

文献摘要

参考文献

被引文献

相似文献

工作温度高于当今最新技术水平的材料可以在多种应用中提高系统性能,并实现新技术。在大多数情况下,需要具有高熔化温度和热力学稳定性以及低离子扩散率的保护性氧化物膜。因此,高温系统的设计将受益于对大量氧化物的这些性质和相关性质的了解。虽然许多氧化物具有某些感兴趣的性质(例如,对于> 1000个氧化物存在弹性常数),对于相对小的子集,熔化温度是已知的。熔化温度的确定在实验和计算上都是耗时且昂贵的;因此,我们使用数据科学工具从现有数据中开发预测模型。由于可用的熔化温度值相对较少,无法使用标准工具,因此我们使用基于迁移学习的多步方法,其中利用第一原理计算的替代数据来使用小数据集开发模型。我们使用这些模型来预测近11,000种氧化物的预期特性,并量化空间中的不确定性。
Materials with higher operating temperatures than today’s state of the art can improve system performance in several applications and enable new technologies. Under most scenarios, a protective oxide scale with high melting temperatures and thermodynamic stability as well as low ionic diffusivity is required. Thus, the design of high-temperature systems would benefit from knowledge of these properties and related ones for a large number of oxides. While some properties of interest are available for many oxides (e.g., elastic constants exist for > 1000 oxides), the melting temperature is known for a relatively small subset. The determination of melting temperatures is time consuming and costly, both experimentally and computationally; thus, we use data science tools to develop predictive models from the existing data. Since the relatively small number of available melting temperature values precludes the use of standard tools, we use a multi-step approach based on transfer learning where surrogate data from first principles calculations are leveraged to develop models using small datasets. We use these models to predict the desired properties for nearly 11,000 oxides and quantify uncertainties in the space.
DOI: 10.1088/1361-651x/ab7150
发表时间: 2020-03
影响因子: 1.8
作者:
E. Giessen;P. Schultz;N. Bertin;V. Bulatov;W. Cai;Gábor Csányi;S. Foiles;M. Geers;C. González;M. Hütter;Woo Kyun Kim;D. Kochmann;J. Llorca;A. Mattsson;J. Rottler;A. Shluger;R. Sills;I. Steinbach;A. Strachan;E. Tadmor
通讯作者: E. Giessen;P. Schultz;N. Bertin;V. Bulatov;W. Cai;Gábor Csányi;S. Foiles;M. Geers;C. González;M. Hütter;Woo Kyun Kim;D. Kochmann;J. Llorca;A. Mattsson;J. Rottler;A. Shluger;R. Sills;I. Steinbach;A. Strachan;E. Tadmor
DOI: 10.1063/1.4812323
发表时间: 2013-07-01
期刊: APL MATERIALS
影响因子: 6.1
作者:
Jain, Anubhav;Shyue Ping Ong;Persson, Kristin A.
通讯作者: Persson, Kristin A.
DOI: 10.1007/978-3-319-08979-9
发表时间: 2019-01
影响因子: 3.4
作者:
P. Perner
通讯作者: P. Perner
DOI: 10.1016/j.jcp.2018.10.045
发表时间: 2019-02-01
影响因子: 4.1
作者:
Raissi, M.;Perdikaris, P.;Karniadakis, G. E.
通讯作者: Karniadakis, G. E.
走向连续爆震波火箭发动机演示器
DOI: --
发表时间: 2006
期刊:
影响因子: --
作者:
F. Falempin;E. Daniau;N. Getin;F. A. Bykovskii;S. A. Zhdan
通讯作者: S. A. Zhdan