Machine Learning for Revealing Spatial Dependence among Nanoparticles: Understanding Catalyst Film Dewetting via Gibbs Point Process Models
Machine Learning for Revealing Spatial Dependence among Nanoparticles: Understanding Catalyst Film Dewetting via Gibbs Point Process Models
复制标题
机器学习揭示纳米粒子之间的空间依赖性：通过吉布斯点过程模型了解催化剂膜去湿
DOI：
10.1021/acs.jpcc.0c07765
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Bedewy, Mostafa
中科院分区：
文献类型：
--
作者：
Aziz Ezzat, Ahmed;Bedewy, Mostafa
我们将现场环境透射电子显微镜(E-TEM)与自动图像处理和统计机器学习相结合，为复杂的纳米级现象独特地建立了可解释的数学模型和精确的模拟工具，这些现象涉及耦合的物理和化学过程以及其他难以建模的相互作用。特别是，随着时间的推移，需要更好地理解、表征和预测密集的金属纳米催化剂群体中的邻近效应。在这里，我们利用统计机器学习的一个分支--点过程理论，从一系列E-TEM图像中“学习”相邻的氧化铝支撑的铁纳米粒子集合之间的空间相关性。我们构建了一组点过程模型来对空间相关性的性质做出统计推断，空间相关性管理着纳米粒子在750°C的乙炔存在下伴随着金属还原而在薄膜去湿过程中的快速形成或“弹出”。我们表明，纳米粒子表现出很强的分散行为，即新的纳米粒子在分散的位置与其现有的领土邻居保持可预测的距离。我们还表明，Gibbs点过程充分描述了这种依赖于时间的空间变化背后的成对相互作用。此外，我们建立在我们的机器学习模型的基础上，开发了一个计算模拟工具，能够以比实验观测更精细的时间分辨率和更大的空间域来生成准确的纳米颗粒形成的时空模拟。这是一种迫切需要的能力，以克服目前支持设计、分析和控制纳米催化剂群体集体行为的计算方法的局限性。
We combinein situenvironmental transmission electron microscopy (E-TEM) with automated image processing and statistical machine learning to uniquely formulate interpretable mathematical models and accurate simulation tools for complex nanoscale phenomena involving coupled physical and chemical processes and interactions that are otherwise hard to model. In particular, there is a need for a better understanding, characterization, and prediction of the proximity effects among dense populations of metal nanocatalysts as they form and evolve over time. Here, we leverage point process theory, a branch of statistical machine learning, to “learn” the spatial dependencies among ensembles of adjacent alumina-supported iron nanoparticles from a time sequence of E-TEM images. We construct a set of point process models to make statistical inferences about the nature of spatial dependencies that govern the rapid formation, or “popping” of nanoparticles during thin film dewetting, concomitant with metal reduction in the presence of acetylene at 750 °C. We show that nanoparticles exhibit strong dispersion behavior, i.e., new nanoparticles pop in dispersed locations at a predictable distance from their existing territorial neighbors. We also show that Gibbs point processes adequately describe the pairwise interactions underlying such time-dependent spatial variations. Further, we build on our machine-learned models to develop a computational simulation tool capable of producing accurate spatiotemporal simulations of nanoparticle formation at finer time resolutions and larger spatial domains than those of experimental observations. This is a much needed capability to overcome current limitations in computational methods supporting the design, analysis, and control of the collective behavior of nanocatalyst populations.
登录
查看更多内容
DOI：
10.1007/s10463-018-0690-9
发表时间：
2019-10-01
影响因子：
1
作者：
Schoenberg, Frederic Paik;Hoffmann, Marc;Harrigan, Ryan J.
通讯作者：
Harrigan, Ryan J.
影响因子：
2.3
作者：
M. Jun;C. Schumacher;R. Saravanan
通讯作者：
M. Jun;C. Schumacher;R. Saravanan
碳纳米管薄膜成核和自组织的高速原位X射线散射。
影响因子：
17.1
作者：
E. Meshot;Eric Verploegen;M. Bedewy;S. Tawfick;A. Woll;K. Green;M. Hromalik;M. Hromalik;L. Koerner;L. Koerner;H. Philipp;M. Tate;S. Gruner;A. Hart
通讯作者：
A. Hart
影响因子：
3.4
作者：
Hajilounezhad, Taher;Ajiboye, Damola M.;Maschmann, Matthew R.
通讯作者：
Maschmann, Matthew R.
TEM 图像分析和建模：在勃姆石纳米颗粒中的应用
影响因子：
2
作者：
M. Moreaud;D. Jeulin;V. Morard;R. Revel
通讯作者：
R. Revel