Knowledge management system National Space Science Center,CAS
Multimodal Deep Learning for Heterogeneous GNSS-R Data Fusion and Ocean Wind Speed Retrieval | |
Alternative Title | WOS:000577878900004 |
Chu, Xiaohan; He, Jie1; Song, Hongqing2; Qi, Yue1; Sun, Yueqiang3,4; Bai, Weihua3,4; Li, Wei3,4; Wu, Qiwu5 | |
Source Publication | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
![]() |
2020 | |
Volume | 13Pages:5971-5981 |
DOI | 10.1109/JSTARS.2020.3010879 |
ISSN | 1939-1404 |
Language | 英语 |
Keyword | Feature extraction Wind speed Data models Sea surface Sea measurements Machine learning Delay-Doppler map (DDM) GNSS-reflectometry (GNSS-R) multimodal deep learning ocean surface wind retrieval SEA-ICE SCATTERING |
Abstract | The comprehensiveness of the raw input data and the effectiveness of feature engineering are two key factors affecting the performance of machine learning. To improve the data comprehensiveness for Global Navigation Satellite System Reflectometry (GNSS-R) ocean wind speed retrieval, this article introduces a new input data structure, which is composed of Delay-Doppler maps (DDM) and all satellite receiver status (SRS) parameters. Then, to overcome the difficulty of handcrafted feature engineering and effectively fusion the information of DDM and SRS, we presented a heterogeneous multimodal deep learning (HMDL) method to retrieve the wind speed according to the heterogeneity of the input data. The proposed model is verified by the performance evaluation of realistic data sets obtained from TDS-1. The new input data structure improves the prediction accuracy at 13.5% to 30.7% on mean absolute error (MAE) at 10.6% to 29.5% on the root mean square error (RMSE). The HMDL improves the prediction accuracy at 7.7% on MAE and 7.1% on RMSE. The whole proposed solution improves the prediction accuracy at 36.3% on MAE and 36.8% on RMSE, comparing with the traditional neural network-based solution. The results clearly show that both the introduction of the new input data structure and HMDL effectively improve the accuracy and robustness of GNSS-R wind speed retrieval. |
Indexed By | SCI |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.nssc.ac.cn/handle/122/7580 |
Collection | 中国科学院国家空间科学中心 |
Affiliation | 1.Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Beijing 100083, Peoples R China 2.Univ Sci & Technol Beijing, Shunde Grad Sch, Shunde 528300, Guangdong, Peoples R China 3.Univ Sci & Technol Beijing, Sch Civil & Resources Engn, Beijing 100083, Peoples R China 4.Chinese Acad Sci, Natl Space Sci Ctr, Beijing Key Lab Space Environm Explorat, Beijing 100190, Peoples R China 5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 6.Engn Univ PAP, Xian 710086, Peoples R China |
Recommended Citation GB/T 7714 | Chu, Xiaohan,He, Jie,Song, Hongqing,et al. Multimodal Deep Learning for Heterogeneous GNSS-R Data Fusion and Ocean Wind Speed Retrieval[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2020,13:5971-5981. |
APA | Chu, Xiaohan.,He, Jie.,Song, Hongqing.,Qi, Yue.,Sun, Yueqiang.,...&Wu, Qiwu.(2020).Multimodal Deep Learning for Heterogeneous GNSS-R Data Fusion and Ocean Wind Speed Retrieval.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,13,5971-5981. |
MLA | Chu, Xiaohan,et al."Multimodal Deep Learning for Heterogeneous GNSS-R Data Fusion and Ocean Wind Speed Retrieval".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 13(2020):5971-5981. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment