"

Cookies ussage consent

I agree.

Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.

Machine learning assisted design of a dispersion-engineered photonic crystal waveguide with U-shaped group index for true time delay applications

RUKHSAR ZAFAR1,* , NAGESH JANRAO2, RAHUL PANDEY3, VINAY KANUNGO1

Affiliation

  1. Department of Electronics and Communication Engineering, Swami Keshvanand Institute of Technology, Management & Gramothan, Jaipur, India
  2. Department of Medical Electronic, Government Polytechnic Institute Nanded, India
  3. School of Computer Science,. University of Petroleum and Energy Studies, Dehradun, India

Abstract

Slow-light photonic crystal waveguides (PCWs) are promising for compact optical delay lines and true time delay (TTD) elements in microwave photonics and beyond-5G communication systems. However, it remains a challenge to achieve a high group index over a broad bandwidth due to strong dispersion near the photonic band edge. In this work, a dispersion-engineered W1 photonic crystal waveguide is designed, and the radii of the first two rows of air holes are systematically tailored to create a U-shaped group-index profile, thereby reducing dispersion over a wider bandwidth. The structure is analyzed using finite-difference time-domain (FDTD) methods and plane wave expansion (PWE). To reduce the need for repeated full-wave simulations, a data-driven regression framework is developed that predicts the group-index–bandwidth product using the hole radii as input. Our comparison shows that the nonlinear regression model performs much better than linear regression, reaching an R2 score of 0.9729 and a low mean squared error of 0.000061. This machine-learning-assisted design method enables fast optimization while maintaining physical accuracy. The proposed slow-light PCW opens avenues for high-delay–bandwidth performance, compact true-time-delay units, optical buffering, and beam steering in next-generation microwave photonic systems.

Keywords

Slow light, Photonic crystal waveguide, Group index, Dispersion, Machine learning.

Citation

RUKHSAR ZAFAR, NAGESH JANRAO, RAHUL PANDEY, VINAY KANUNGO, Machine learning assisted design of a dispersion-engineered photonic crystal waveguide with U-shaped group index for true time delay applications, Optoelectronics and Advanced Materials - Rapid Communications, 20, 9-10, September-October 2026, pp.428-435 (2026).

Submitted at: March 10, 2026

Accepted at: Oct. 5, 2026