Predictive residual neural networks for optical trapping of small particles

Optical tweezers provide a non-contact method to trap, move, and manipulate micro- and nano-sized objects. Using properly designed dielectric and plasmonic nanostructure configurations, optical tweezers have been tailored to create stable and precise trapping for nanoscale objects. Recent advances in numerical optimization techniques allow further enhancement in nanoscale optical traps through inverse optimization of such configurations. One of the main challenges in such optimization approaches is the time-consuming nature of full-wave simulation of nanostructures and postprocessing steps to extract optical forces. To address this challenge, we introduce a surrogate solver based on residual neural networks that can accurately predict the forces exerted on a nanoparticle. Our results illustrate the possibility of capturing the highly nonlinear dynamics of local optical forces using moderate-sized datasets, particularly appealing to the inverse design of optical tweezers.