Prof. Sebastian Troia and Prof. Massimo Tornatore from the Department of Electronics, Information and Bioengineering at Politecnico di Milano have been honoured with the 2026 IEEE Communications Society Charles Kao Award for Best Optical Communications & Networking Paper for their paper, "Towards Explainable Artificial Intelligence in Optical Networks: The Use Case of Lightpath QoT Estimation," co-authored with Omran Ayoub, Davide Andreoletti, Andrea Bianco, Silvia Giordano, and Cristina Rottondi.
The Charles Kao Award recognizes the most outstanding paper published in the IEEE/Optica Journal of Optical Communications and Networking, highlighting research excellence and innovation in optical communications and networking.
This prestigious recognition underscores the growing importance of explainable artificial intelligence in the design and management of next-generation optical networks, paving the way for more transparent, trustworthy, and intelligent communication infrastructures.
More specifically, the paper explores how explainable artificial intelligence can make machine learning models more transparent and trustworthy in optical networks. Focusing on the estimation of light path transmission quality, it shows how interpretability methods can help identify which factors influence a model’s predictions and understand why some errors occur. In this way, the study moves beyond prediction accuracy and highlights the importance of making artificial intelligence decisions clearer and more reliable for network operators.