# Mitigating Spectral Bias in Neural Operators for Underwater Transmission Loss Prediction

arXiv: https://arxiv.org/abs/2608.18141 · HTML: https://mlsanity.com/paper/2608.18141/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Machine learning in acoustics: theory and applications](https://mlsanity.com/paper/1905.04418/) (2019)
- [Convolutional Neural Network Modelling for MODIS Land Surface Temperature Super-Resolution](https://mlsanity.com/paper/2202.10753/) (2022)
- [Sound Field Reconstruction Using Physics-Informed Boundary Integral Networks](https://mlsanity.com/paper/2506.03917/) (2025)
- [Hankel-FNO: Fast Underwater Acoustic Charting Via Physics-Encoded Fourier Neural Operator](https://mlsanity.com/paper/2512.06417/) (2025)

## Abstract (arXiv)

Predicting underwater acoustic transmission loss rapidly and accurately is crucial for real-time ocean acoustic applications. While Fourier Neural Operators (FNO) have emerged as powerful surrogate models due to their global receptive fields, they suffer from spectral bias. The frequency truncation mechanism in FNO filters out high-frequency components, resulting in over-smoothed predictions that fail to capture fine-grained interference patterns. To overcome this limitation, this paper proposes a Spectral-Spatial Residual Learning (S2RL) framework. S2RL decomposes the prediction task into a coarse-to-fine process: a spectral Global Propagator first generates a globally consistent prediction, and a spatial Local Refiner subsequently recovers the high-frequency residuals. Experimental results on a South China Sea dataset show that the proposed method significantly outperforms FNO baselines while maintaining millisecond-level inference speeds.