Fiber Optic Sensing in Rain Detection Using Unsupervised Domain Adaptation
Published in Galileo conference: Fibre Optic Sensing in Geosciences, 2024
This work proposes a distributed acoustic sensing (DAS)–based framework for rain intensity classification using existing telecommunication fiber networks. We develop a CNN with unsupervised domain adaptation (DRCN) to learn domain-robust representations from unlabeled field data collected across multiple environments. Results demonstrate reliable cross-domain rain detection performance, highlighting the feasibility of scalable weather sensing using already-deployed fiber infrastructure.
Recommended citation: Ding, Y., Shi, S., Tian, Y., Jiang, Z., Ozharar, S., Wang, T., and Moore, J.: Fiber Optic Sensing in Rain Detection Using Unsupervised Domain Adaptation, Galileo conference: Fibre Optic Sensing in Geosciences, Catania, Italy, 16–20 Jun 2024, GC12-FibreOptic-87, https://doi.org/10.5194/egusphere-gc12-fibreoptic-87, 2024.