Deep-learning empowered unique and rapid optimization of meta-absorbers for solar thermophotovoltaics

Abstract

Optical nano-structure designs usually employ computationally expensive and timeintensive electromagnetic (EM) simulations that call for resorting to modern-day data-oriented methods, making design robust and quicker. A unique dataset and hybrid image processing model combining a CNN with gated recurrent units is presented to foresee the EM absorption response of photonic nano-structures. An inverse model is also discussed to predict the optimum geometry and dimensions of meta-absorbers. Mean-squared error of the order of 10-3 and an accuracy of 99% is achieved for trained models, and the average prediction time for the DL models is around 98% faster than that of simulations. This idea strengthens the proposition that efficient DL-based solutions can substitute the traditional methods for designing nano-optical structures.