An inverse design paradigm of multi-functional elastic metasurface via data-driven machine learning

Elastic metasurfaces have become one of the most promising platforms for manipulating mechanical wavefronts with the striking feature of ultra-thin geometry. The conventional design of mechanical metasurfaces significantly relies on numerical, trial-and-error methods to identify structural parameters of the unit cells, which requires huge computational resources and could be extremely challenging if the metasurface is multi-functional. Machine learning technique provides another powerful tool for the design of multi-functional elastic metasurfaces because of its excellent capability in building nonlinear mapping relation between high-dimensional input data and output data. In this paper, a machine learning network is introduced to extract the complex relation between high-dimensional geometrical parameters of the metasurface unit and its high-dimensional dynamic properties. Based on a big dataset, the welltrained network can play the role of a surrogate model in the inverse design of a multi-functional elastic metasurface to significantly shorten the time for the design. Such method can be conveniently extended to design other multi-functional metasurfaces for the manipulation of optical, acoustical or mechanical waves.(c) 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

Elastic metasurfaces have the potential to manipulate mechanical wavefronts with their ultra-thin geometry. Conventional design methods rely heavily on numerical and trial-and-error approaches, which can be computationally expensive and challenging for multi-functional metasurfaces. This paper introduces a machine learning network that can extract the complex relation between geometrical parameters and dynamic properties of the metasurface unit, enabling faster design.