SCAWaveNet: A Spatial-Channel Attention-Based Network for Global Significant Wave Height Retrieval

TL;DR

SCAWaveNet is a novel deep learning model that employs spatial-channel attention mechanisms to improve the accuracy of global significant wave height retrieval from spaceborne GNSS data, outperforming existing models.

Contribution

The paper introduces SCAWaveNet, a new attention-based neural network that effectively fuses spatial and channel information for enhanced wave height estimation.

Findings

Achieves RMSE of 0.438 m with ERA5 data

Reduces RMSE by at least 3.52% compared to state-of-the-art

Outperforms existing models on buoy observation data

Abstract

Recent advancements in spaceborne GNSS missions have produced extensive global datasets, providing a robust basis for deep learning-based significant wave height (SWH) retrieval. While existing deep learning models predominantly utilize CYGNSS data with four-channel information, they often adopt single-channel inputs or simple channel concatenation without leveraging the benefits of cross-channel information interaction during training. To address this limitation, a novel spatial-channel attention-based network, namely SCAWaveNet, is proposed for SWH retrieval. Specifically, features from each channel of the DDMs are modeled as independent attention heads, enabling the fusion of spatial and channel-wise information. For auxiliary parameters, a lightweight attention mechanism is designed to assign weights along the spatial and channel dimensions. The final feature integrates both spatial and channel-level characteristics. Model performance is evaluated using four-channel CYGNSS data. When ERA5 is used as a reference, SCAWaveNet achieves an average RMSE of 0.438 m. When using buoy data from NDBC, the average RMSE reaches 0.432 m. Compared to state-of-the-art models, SCAWaveNet reduces the average RMSE by at least 3.52% on the ERA5 dataset and by 5.68% on the NDBC buoy observations. The code is available at https://github.com/Clifx9908/SCAWaveNet.