Scopus Indexed Publications

Paper Details


Title
Predicting terahertz properties in PCF-based Kagome lattice structure using deep learning

Author
, Kawsar Ahmed, Md Mamun Ali,

Email

Abstract

This paper describes a deep learning (DL) based framework for accurately and efficiently predicting important electromagnetic parameters in Kagome photonic crystal fibers (PCFs) in the terahertz (THz) regime. A tailored multilayer perceptron (MLP) was trained on high-fidelity FEM simulation data for the prediction of effective refractive indices (n_eff-X, n_eff-Y), effective area A_eff, and dispersion with high accuracy. The model achieved R² values higher than 0.9996 and provided a computational speed-up of more than 400,000 times compared to simulation using conventional methods. In contrast to the problem of space complexity, our model needed just 2464 samples for training and continued to exhibit excellent generalizing performance. The framework proposed here can support inverse design, enabling the retrieval of structural parameters with an error of ≤ 2.5% in real-time. Optimized designs exhibited ultra-low Aeff (2.76 × 10⁴ μm²) and flatband dispersion flattening (±0.00325 ps/nm·km, 0.8–1.5 THz), surpassing those previously published designs. This work establishes a new benchmark for data-driven PCF design and presents a vision for a transformative impact on terahertz photonics through deep learning.


Keywords

Journal or Conference Name
Optik

Publication Year
2026

Indexing
scopus