Tunable Plasmonic Absorption in Metal-Dielectric Multilayers via FDTD Simulations and an Explainable Machine Learning Approach

Abstract

Plasmonic devices, fundamental to modern nanophotonics, exploit resonant interactions between light and free electrons in metals to achieve enhanced light trapping and electromagnetic field confinement. However, modeling their complex, nonlinear optical responses remains computationally intensive. In this work, we combine finite-difference time-domain simulations with machine learning to simulate and predict absorbed power behavior in multilayer plasmonic stacks composed of SiO2, gold, silver, and indium tin oxide. By varying Au and Ag thicknesses (10-50nm) across a spectral range of 300-1500nm, we generate spatial absorption maps and integrated power metrics from full-wave solutions to Maxwell's equations. A multilayer perceptron models global absorption behavior with a mean absolute error of 0.0953, while a convolutional neural network predicts spatial absorption distributions with an MAE of 0.0101. SHapley Additive exPlanations identify plasmonic layer thickness and excitation wavelength as dominant contributors to absorption, which peaks between 450 and 850~nm. Gold demonstrates broader and more sustained absorption compared to silver, although both metals exhibit reduced efficiency outside the resonance window. This integrated FDTD-ML framework offers a fast, explainable, and accurate approach for investigating tunable plasmonic behavior in multilayer systems, with applications in optical sensing, photovoltaics, and nanophotonic device design.