Deep-Learning-Enabled Inverse Engineering of Multi-Wavelength Invisibility-to-Superscattering Switching with Phase-Change Materials

TL;DR

This paper demonstrates how deep learning can efficiently inverse design multilayer nanoparticles with tunable scattering properties, enabling dynamic switching between invisibility and superscattering at multiple wavelengths using phase-change materials.

Contribution

It introduces a neural network approach for inverse design of complex nanoparticles with dynamic scattering control, simplifying the traditionally complex design process.

Findings

Neural network accurately predicts scattering spectra.

Efficient inverse design of nanoparticle structures.

Achieves multi-wavelength invisibility-to-superscattering switching.

Abstract

Inverse design of nanoparticles for desired scattering spectra and dynamic switching between the two opposite scattering anomalies, i.e. superscattering and invisibility, is important in realizing cloaking, sensing and functional devices. However, traditionally the design process is quite complicated, which involves complex structures with many choices of synthetic constituents and dispersions. Here, we demonstrate that a well-trained deep-learning neural network can handle these issues efficiently, which can not only forwardly predict scattering spectra of multilayer nanoparticles with high precision, but also inversely design the required structural and material parameters efficiently. Moreover, we show that the neural network is capable of finding out multi-wavelength invisibility-to-superscattering switching points at the desired wavelengths in multilayer nanoparticles composed of metals and phase-change materials. Our work provides a useful solution of deep learning for inverse design of nanoparticles with dynamic scattering spectra by using phase-change materials.