Multi-Tech Sensing In-Field Demonstration on Terrestrial Optical Data Networks

Transforming optical transport networks into a distributed sensing grid is a promising pathway to enhance infrastructure resilience and environmental awareness. To achieve widespread scalability without disrupt- ing data traffic, operators can exploit the synergy between different sensing techniques naturally coexisting on the same infrastructure. In this paper, we present an in-field demonstration of a multi-technique sensing framework operating on live terrestrial optical networks, combining interferometric phase sensing and State of Polarization (SOP) monitoring. We first propose and validate an unsupervised anomaly detection pipeline based on autoencoders, applied to a 38 km regional link connecting Ascoli Piceno and Teramo (Italy) and show some examples of detected events. This framework proves capable of automatically identifying signal anomalies across different physical observables without relying on manual labeling. Subsequently, we move to a metropolitan urban scenario in the city of Turin and assess a multi-tech sensing analysis using coherent transceivers and state-of-polarization metrics obtained from polarimeters and cost-effective polarization beam splitters-based device. We highlight the correlation between specific sensing metrics and standard network telemetry data, such as Bit Error Rate (BER) and temperature, and validate the system capability to detect mechanical perturbations originated by human activity along the cable or by controlled experiments using a robotic arm. These results confirm the feasibility of aggregating heterogeneous data sources into a unified sensing plane to enable pervasive infrastructure supervision.