English NewsSunday, 15 November 2026
Latest
AI

Peer-reviewed optical-fibre sensor estimates underwater flow with a ResNet-LSTM model

2026-08-18

Peer-reviewed optical-fibre sensor estimates underwater flow with a ResNet-LSTM model
Photo: ell brown (CC BY-SA 2.0)

In a journal article dated 16 August 2026, Haiqing Li, Boxue Sun, Xiaonan Bian, Yujia Wang and Xianping Fu describe a biomimetic U-shaped plastic optical-fibre sensor with a cilium-like cantilever and a hybrid ResNet-LSTM model. Performance figures are author-reported.

The authors report a mean velocity error of 0.0105 m/s and a direction error of 1.51 degrees.

The sensor could help underwater navigation and inspection, but field robustness, fouling, calibration drift, transfer to turbulent conditions and independent reproduction remain unresolved.

More AI technology news