Design of acoustic absorbing metasurfaces using a data-driven approach

The design of acoustic metasurfaces with desirable properties is challenging due to their artificial nature and the large space of physical and geometrical parameters. Until recently, design strategies were primarily based on numerical simulations based on finite-element or finite-difference time-domain methods, which are limited in terms of computational speed or complexity. Here, we present an efficient two-stage data-driven approach for analyzing and designing membrane-type metasurface absorbers with desirable characteristics. In the first stage, a forward model consisting of a neural network is trained to map an input, comprising the membrane parameters, to the observed sound absorption spectrum. In the second stage, the learned forward model is inverted to infer the input parameters that produce the desired absorption response. The metasurface membrane parameters, which serve as input to the neural network, are estimated by minimizing a loss function between the desired absorption profile and the output of the learned forward model. Two devices are then fabricated using the estimated membrane parameters. The measured acoustic absorption responses of the fabricated devices show a very close agreement with the desired responses. Designing artificial acoustic metasurfaces via traditional numerical simulations is computationally challenging. Here, the authors introduce a data-driven neural network approach for the inverse design of membrane-type sound absorbers, testing the desired properties on two devices fabricated using model-estimated parameters.