Inverse design of nano-photonic wavelength demultiplexer with a deep neural network approach

TL;DR

This paper introduces a pre-trained neural network approach for inverse design of nano-photonic devices, demonstrating high accuracy and robustness with limited training data in designing a wavelength demultiplexer.

Contribution

The paper presents a novel pre-trained combined neural network (PTCN) method that enhances inverse design accuracy and data efficiency for integrated photonic circuits.

Findings

Prediction correlation coefficient > 0.974 with only 17% training data.

Achieved a wavelength demultiplexer with -2dB transmission loss.

Demonstrated low reflection and crosstalk in the device.

Abstract

In this paper, we propose a pre-trained-combined neural network (PTCN) as a comprehensive solution to the inverse design of an integrated photonic circuit. By utilizing both the initially pre-trained inverse and forward model with a joint training process, our PTCN model shows remarkable tolerance to the quantity and quality of the training data. As a proof of concept demonstration, the inverse design of a wavelength demultiplexer is used to verify the effectiveness of the PTCN model. The correlation coefficient of the prediction by the presented PTCN model remains greater than 0.974 even when the size of training data is decreased to 17%. The experimental results show a good agreement with predictions, and demonstrate a wavelength demultiplexer with an ultra-compact footprint, a high transmission efficiency with a transmission loss of -2dB, a low reflection of -10dB, and low crosstalk around -7dB simultaneously.