Single Mode rib waveguide design using Machine Learning techniques

Abstract

This work aim to determine a Single Mode (SM) Silicon-On-Insulator (SOI) rib waveguide using Machine learning (ML) techniques, which learn automatically by matching the input data with the target property. Random Forest (RF) is the ML algorithm used in this work. The accuracy of the model reaches 99% by using R2 score. The device is a rib waveguide based on Silicon (Si), with a cladding made of Silica (SiO2). The results obtained illustrate the conditions for SM, with the width and the rib etch-depth found to be relatively smaller compared to the total thickness. The ML approach have proven to be quick and effective regarding this problem.