# Machine Learning for QoT Estimation of Unseen Optical Network States

## TL;DR

This paper introduces a deep graph convolutional neural network approach to estimate the quality of transmission in optical networks, effectively capturing complex impairments like inter-core crosstalk in unseen network states.

## Contribution

It presents a novel application of deep graph convolutional neural networks for QoT estimation, including impairments like inter-core crosstalk in optical networks.

## Key findings

- Effective estimation of QoT for unseen network states.
- Captures inter-core crosstalk impairments.
- Demonstrates improved accuracy over traditional methods.

## Abstract

We apply deep graph convolutional neural networks for Quality-of-Transmission estimation of unseen network states capturing, apart from other important impairments, the inter-core crosstalk that is prominent in optical networks operating with multicore fibers.