Hot Paper - Hybrid artificial neural networks and analytical model for prediction of optical constants and bandgap energy of 3D nanonetwork silicon structures

Hybrid artificial neural networks and analytical model for prediction of optical constants and bandgap energy of 3D nanonetwork silicon structures

用于预测 3D 纳米网络硅结构的光学常数和带隙能量的混合人工神经网络和分析模型
3Dナノネットワークシリコン構造の光学定数とバンドギャップエネルギーを予測するためのハイブリッド人工ニューラルネットワークと分析モデル
3차원 나노 네트워크 실리콘 구조의 광학 상수 및 밴드갭 에너지 예측을 위한 하이브리드 인공 신경망 및 분석 모델
Redes neuronales artificiales híbridas y modelo analítico para la predicción de constantes ópticas y energía de banda prohibida de estructuras de silicio de nanorred 3D
Réseaux de neurones artificiels hybrides et modèle analytique pour la prédiction des constantes optiques et de l'énergie de bande interdite des structures de silicium de nanoréseau 3D
Гибридные искусственные нейронные сети и аналитическая модель для прогнозирования оптических констант и запрещенной энергии кремниевых структур трехмерных наносетей

Shreeniket Joshi, Amirkianoosh Kiani

Silicon Hall: Micro/Nano Manufacturing Facility, Faculty of Engineering and Applied Science, Ontario Tech University, 2000 Simcoe St N, Oshawa, Ontario L1G 0C5, Canada

https://doi.org/10.29026/oea.2021.210039

https://www.oejournal.org/article/doi/10.29026/oea.2021.210039

Opto-Electronic Advances, 25 September 2021

Abstract

The aim of this study is to develop a reliable method to determine optical constants for 3D-nanonetwork Si thin films manufactured using a pulsed-laser ablation technique that can be applied to other materials synthesized by this technique. An analytical method was introduced to calculate optical constants from reflectance and transmittance spectra.

Optical band gaps for this novel material and other important insights on the physical properties were derived from the optical constants. The existing optimization methods described in the literature were found to be complex and prone to errors while determining optical constants of opaque materials where only reflectance data is available.

A supervised Deep Learning Algorithm was developed to accurately predict optical constants from the reflectance spectrum alone. The hybrid method introduced in this study was proved to be effective with an accuracy of 95%.

Reviews and Discussions