期刊
INTEGRATING MATERIALS AND MANUFACTURING INNOVATION
卷 10, 期 4, 页码 689-695出版社
SPRINGER HEIDELBERG
DOI: 10.1007/s40192-021-00242-3
关键词
Materials informatics; Inverse design; Materials discovery
This approach shifts the optimization focus to the fractions of each element in a composition, using a pretrained network and a custom loss function to optimize material compositions. Fractional optimization is expected to excel in inverse design problems concerning the effects of dopants and balancing competing properties.
Traditional, data-driven materials discovery involves screening chemical systems with machine learning algorithms and selecting candidates that excel in a target property. The number of screening candidates grows infinitely large as the fractional resolution of compositions and the number of included elements increase. The computational infeasibility and probability of overlooking a successful candidate grow likewise. Our approach takes inspiration from neural style transfer and shifts the optimization focus from model parameters to the fractions of each element in a composition. By leveraging a pretrained network with exceptional prediction accuracy (CrabNet) and writing a custom loss function to govern a vector consisting of element fractions, material compositions can be optimized such that a predicted property is maximized or minimized. It is expected that fractional optimization would excel in inverse design problems concerning the effects of dopants and those seeking a balance between competing properties.
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