Efficient Hotspot Switching in Plasmonic Nanoantennas using Phase-shaped Laser Pulses controlled by Neural Networks

TL;DR

This paper introduces a neural network-based method for controlling and switching hotspots in plasmonic nanoantennas using phase-shaped laser pulses, enabling precise manipulation at sub-diffraction scales.

Contribution

It demonstrates the use of neural networks to predict and control near-field hotspots in nanoantennas through spectral phase shaping, including transfer learning for different geometries.

Findings

Neural networks can predict hotspot intensities based on spectral phase.

Deterministic hotspot switching is achievable with phase-shaped pulses.

Transfer learning allows adaptation to different nanoantenna geometries.

Abstract

We present a novel procedure for manipulating the near-field of plasmonic nanoantennas using neural network-controlled laser pulse-shaping. As model systems we numerically studied the spatial distribution of the second harmonic response of L-shaped nanoantennas illuminated by broadband laser pulses. We first show that a trained neural network can be used to predict the relative intensity of the second-harmonic hotspots of the nanoantenna for a given spectral phase and that it can be employed to deterministically switch individual hotspots on and off on sub-diffraction length scale by shaping the spectral phase of the laser pulse. We then demonstrate that a neural network trained on a $90~\mathrm{nm} \times 150~\mathrm{nm}$ nano-L can in addition efficiently predict the hotspot intensities in an antenna with different aspect ratio after minimal further training for varying spectral phases. These results could lead to novel applications of machine-learning and optical control to nanoantennas and nanophotonics components.