TreeEventID a system for accurate tree hazard detection on aerial telecom cables using distributed fiber sensing and novel InfoNCE-based learning
Disclosed are systems, methods, and structures that employ distributed fiber sensing that utilizes existing fiber cables for detecting tree events. Our inventive systems and methods can detect when a tree or other types of vibration occur on the telecom cable or poles, creating a high-resolution spatial profile of the cable. Systems and methods according to aspects of the present disclosure distinguish between tree events and other vibrations, such as hammer strikes on a utility pole, by employing Information Noise Contrastive Estimation (InfoNCE) and contrastive learning. Our inventive approach accurately differentiates between different types of vibrations and identifies patterns specific to tree events.
1 . A distributed fiber optic sensing (DFOS) system for aerial cable, tree-hazard detection comprising:
a DFOS system including:
a DFOS interrogator; and
a DFOS optical sensor fiber configured as an aerial cable;
wherein the DFOS interrogator is configured to generate optical interrogator pulses, introduce the generated optical pulses into DFOS optical sensor fiber receive backscattered signals in response;
the DFOS system CHARACTERIZED IN THAT:
Information Noise Contrastive Estimation (InfoNCE) and contrastive learning is employed to distinguish tree events and other vibrations.
2 . The system of claim 1 wherein the system is configured to employ the InfoNCE, a self-supervised learning, to measure similarity between tree event data and other vibration event data.
3 . The system of claim 2 wherein the system is configured to employ contrastive learning to learn vibration patterns that are specific to tree events.
4 . The system of claim 3 , that is trained on a dataset of both tree and non-tree events such that it may distinguish between the tree and non-tree events based on InfoNCE similarity.
5 . The system of claim 4 wherein the DFOS optical sensor fiber is part of an existing telecommunications infrastructure.
6 . The system of claim 5 wherein the system is a central-server system or a cloud-based system.
7 . The system of claim 6 wherein the contrastive learning is performed using a Convolutional Neural Network (CNN).