Characterization of perfect sinusoidal grating profile using artificial neural network for plasmonic based sensors

• Moustapha Godi Tchéré, Stephane Robert, Bernard Bayard, Julie Dutems, Hugo Bruhier, Yves JOURLIN, and damien jamon
• received 01/25/2024; accepted 04/14/2024; posted 04/15/2024; Doc. ID 520109
• Abstract: In this paper, we present a system intended to detect a targeted perfect sinusoidal profile of a diffraction gratingduring its manufactured process. Indeed, the sinusoidal nature of the periodic structure is essential to ensureoptimal efficiency of specific applications as plasmonic sensors (Surface Plasmon Resonance SPR based sensors).A neural network is implemented to characterize the geometrical shape of the structure under testing at the endof the Laser Interference Lithography (LIL) process. This decision tool operates in classifier mode prior to furtherprocessing. Then, the geometrical parameters of the structure can be reliably determined if necessary. Twosolutions can be considered: the detection of a fixed geometrical shape operating on a binary mode and theidentification of a geometrical shape from a limited number of profiles. These methods are validated in the contextof plasmonic sensors on experimental sinusoidal grating structures with a grating period of 627 nm.