# Weather-Adaptive Multi-Step Forecasting of State of Polarization Changes in Aerial Fibers Using Wavelet Neural Networks

arXiv: https://arxiv.org/abs/2409.03663 · HTML: https://mlsanity.com/paper/2409.03663/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 0 of its 9 references that are in the map.
- First posted on arXiv 5 Sep 2024.

## Abstract (arXiv)

We introduce a novel weather-adaptive approach for multi-step forecasting of multi-scale SOP changes in aerial fiber links. By harnessing the discrete wavelet transform and incorporating weather data, our approach improves forecasting accuracy by over 65% in RMSE and 63% in MAPE compared to baselines.