Surface-enhanced Raman spectroscopy (SERS) is a highly sensitive and molecule-specific detection technique that uses surface plasmon resonances to enhance Raman scattering from analytes. In SERS system design, the substrates must have minimal or no background at the incident laser wavelength and large Raman signal enhancement via plasmonic confinement and grating modes over large areas (i.e., squared millimeters). These requirements impose many competing design constraints that make exhaustive parametric computational optimization of SERS substrates prohibitively time consuming. Here, we demonstrate a genetic-algorithm (GA)-based optimization method for SERS substrates to achieve strong electric field localization over wide areas for reconfigurable and programmable photonic SERS sensors. We analyzed the GA parameters and tuned them for SERS substrate optimization in detail. We experimentally validated the model results by fabricating the predicted nanostructures using electron beam lithography. The experimental Raman spectrum signal enhancements of the optimized SERS substrates validated the model predictions and enabled the generation of a detailed Raman profile of methylene blue fluorescence dye. The GA and its optimization shown here could pave the way for photonic chips and components with arbitrary design constraints, wavelength bands, and performance targets.
COVID-19 is detected using reverse transcription polymerase chain reaction (RT-PCR) of nasal swabs. A very sensitive and rapid detection technique using easily-collected fluids like saliva must be developed for safe and precise mass testing. Here, we introduce a metasurface platform for direct sensing of COVID-19 from unprocessed saliva. We computationally screen gold metasurfaces out of a pattern space of 2 100 combinations for strongly-enhanced light-virus interaction with machine learning and use it to investigate the presence and concentration of the SARS-CoV-2. We use machine learning to identify the virus from Raman spectra with 95.2% sensitivity and specificity on 36 PCR positive and 33 negative clinical samples and to distinguish wild-type, alpha, and beta variants. Our results could pave the way for effective, safe and quantitative preventive screening and identification of variants.