Sputtering of a single-element material surface by monatomic ion impact is one of the simplest and most fundamental phenomena of plasma–surface interaction. Despite its seemingly simple and well-defined nature, its collision cascade dynamics is so complex that no widely applicable formula of the sputtering yield has ever been derived analytically from the first principles. When the first-principles approach to a complex problem fails to unveil its nature, a data-driven approach, or machine learning, may be used to transform the problem into a tractable model. In this study, regression models of sputtering yields of such systems were constructed based on publicly available data derived from a large number of past experiments. The analysis has also identified the descriptors (i.e., physical variables characterizing the surface and incident ion species) on which the sputtering phenomena depend most strongly and presented quantitative evaluation on how sensitively the regression models depend on each descriptor or group of descriptors. Information obtained in this study can facilitate an understanding of the fundamental workings of the sputtering phenomena in the absence of rigorous analytical theory.
Characterization of descriptors in machine learning for data-based sputtering yield prediction
Note: This paper is part of the Special Collection: Invited Papers from the 2nd International Conference on Data-Driven Plasma Science.
Hiori Kino, Kazumasa Ikuse, Hieu-Chi Dam, Satoshi Hamaguchi; Characterization of descriptors in machine learning for data-based sputtering yield prediction. Phys. Plasmas 1 January 2021; 28 (1): 013504. https://doi.org/10.1063/5.0006816
Download citation file: