# Mode Visualization and Control of Complex Lasers Using Neural Networks

**Authors:** Wai Kit Ng, T. V. Raziman, Dhruv Saxena, Korneel Molkens, Ivo Tanghe, Zhenghe Xuan, Pieter Geiregat, Dries Van Thourhout, Mauricio Barahona, Riccardo Sapienza

PMC · DOI: 10.1021/acsphotonics.5c01710 · ACS Photonics · 2025-09-09

## TL;DR

This paper introduces a new method using neural networks to visualize and control complex laser systems by reconstructing hidden mode features.

## Contribution

The novel contribution is an experimental spectroscopy method using artificial neural networks to visualize and control lasing modes in complex photonic systems.

## Key findings

- A neural network successfully reconstructs spatial gain distributions of lasing modes in a disordered microring array laser.
- A tandem neural network can control laser emission by selectively enhancing targeted modes.
- The method reveals hidden spatial mode features without prior knowledge of the laser device.

## Abstract

Visualizing the behavior of complex laser systems is
an outstanding
challenge, especially in the presence of nonlinear mode interactions.
Hidden features, such as the gain distributions and spatial localization
of lasing modes, often cannot be revealed experimentally, yet they
are crucial to determining the laser action. Here, we introduce an
experimental lasing spectroscopy method that visualizes the gain profiles
of the modes in a complex, disorderly coupled microring array laser
using an artificial neural network. The spatial gain distributions
of the lasing modes are reconstructed without prior knowledge of the
laser device. We further extend the neural network to a tandem neural
network that can control the laser emission by matching the modal
gain/loss profile to selectively enhance the targeted modes. This
mode visualization method offers a new approach to extracting hidden
spatial mode features from photonic structures, which could improve
our understanding and control of complex photonic systems.

## Full-text entities

- **Chemicals:** SiO2 (MESH:D012822), CdSe/CdS (-), SiN (MESH:C032734), CF4 (MESH:C035066), toluene (MESH:D014050)

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC12532367/full.md

## Figures

3 figures with captions in the complete paper: https://tomesphere.com/paper/PMC12532367/full.md

## References

43 references — full list in the complete paper: https://tomesphere.com/paper/PMC12532367/full.md

---
Source: https://tomesphere.com/paper/PMC12532367