期刊
JOURNAL OF PHYSICAL CHEMISTRY LETTERS
卷 11, 期 12, 页码 4625-4630出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.jpclett.0c01128
关键词
-
类别
资金
- National Science Foundation [DGE-1735325]
- University of California, Los Angeles
- Jeffery and Helo Zink Endowed Profesional Development Term Chair
- UCLA Institutional Improvement Grant [IIP 19-11]
Neural networks, trained on data generated by a microkinetic model and finite-element simulations, expand explorable parameter space by significantly accelerating the predictions of electrocatalytic performance. In addition to modeling electrode reactivity, we use micro/nanowire arrays as a well-defined, easily tuned, and experimentally relevant exemplary morphology for electrochemical nitrogen fixation. This model system provides the data necessary for training neural networks which are subsequently exploited for electrocatalytic material morphology optimizations and explorations into the influence of geometry on nitrogen fixation electrodes, feats untenable without large-scale simulations, on both a global and a local basis.
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