Hybrid CNN-Transformer Network With a Weighted MSE Loss for Global Sea Surface Wind Speed Retrieval From GNSS-R Data
Top Cited Papers
- 27 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-13
Abstract
The global navigation satellite system reflectometry (GNSS-R) plays a crucial role in sea surface wind speed measurement, and convolutional neural networks (CNNs) have been a widely used method for wind speed retrieval from GNSS-R data. However, CNNs have limitations in global feature extraction due to the fixed convolutional kernels. Moreover, current studies on wind speed retrieval from GNSS-R data exhibit significant overfitting at low wind speed and underestimation at high wind speed due to the extremely imbalanced data distribution. To address these issues, a hybrid CNN-transformer network (CTN) with a weighted mean square error (mse) loss is proposed in this study. Specifically, the designed CTN incorporates CNN and transformer encoder blocks to capture local and global features, with a dedicated feature fusion module to integrate these features. In addition, a novel weighted mse loss function is designed to tackle the issue of imbalanced data distribution and enhance the estimation accuracy at high wind speeds. The proposed method is validated on Cyclone GNSS (CYGNSS) data and demonstrates improved performance compared with other machine learning algorithms. It achieves a root mean square difference (RMSD) of 1.417 m/s compared to the European Center for Medium-Range Weather Forecasts (ECMWF) reanalysis data and 1.620 m/s compared to the buoy data from the National Data Buoy Center (NDBC). Notably, the proposed model trained with the weighted mse loss function shows an improvement of 20.3% in RMSD for samples with wind speeds exceeding 15 m/s, highlighting the effectiveness of the designed loss function in handling high wind speed data.Keywords
Funding Information
- Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery (RGPIN-2024-04442)
This publication has 47 references indexed in Scilit:
- A review of the BuFeng-1 GNSS-R mission: calibration and validation results of sea surface and land surfaceGeo-spatial Information Science, 2024
- An inland water detection method based on CYGNSSRemote Sensing Letters, 2023
- DDM-Former: Transformer networks for GNSS reflectometry global ocean wind speed estimationRemote Sensing of Environment, 2023
- Information fusion for GNSS-R wind speed retrieval using statistically modified convolutional neural networkRemote Sensing of Environment, 2022
- GNSS reflectometry global ocean wind speed using deep learning: Development and assessment of CyGNSSnetRemote Sensing of Environment, 2022
- Analysis of coastal wind speed retrieval from CYGNSS mission using artificial neural networkRemote Sensing of Environment, 2021
- Temporal variability of GNSS-Reflectometry ocean wind speed retrieval performance during the UK TechDemoSat-1 missionRemote Sensing of Environment, 2020
- An Arctic sea ice multi-step classification based on GNSS-R data from the TDS-1 missionRemote Sensing of Environment, 2019
- An overview of global ocean wind energy resource evaluationsRenewable and Sustainable Energy Reviews, 2016
- Assessment of the global ocean wind energy resourceRenewable and Sustainable Energy Reviews, 2014