Two-dimensional silicon-based dielectric column photonic crystal point defect microcavity Neural network modelling

Abstract

In order to solve the problem that it is difficult to predict the microcavity photonic energy bands of point defects in two-dimensional silicon-based dielectric column photonic crystals, this paper proposes a method to predict the microcavity photonic energy bands of point defects in two-dimensional silicon-based photonic crystals by using an artificial neural network model. In this paper, the energy band structure of triangular lattice point defects at different radii is calculated using MPB, and a neural network model is established based on this data and the accuracy of the established model is verified.