A MACHINE LEARNING FRAMEWORK FOR REAL DATA GNSS-R WIND SPEED RETRIEVAL

被引：0

作者：

Liu, Yunxiang ^{[1
]}

Wang, Jun ^{[1
]}

Collett, Ian ^{[1
]}

Morton, Y. Jade ^{[1
]}

机构：

[1] Univ Colorado, Colorado Ctr Astrodynam Res, Smead Aerosp Engn Sci, Boulder, CO 80309 USA

来源：

2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019) | 2019年

关键词：

CYGNSS; GNSS-R; wind speed retrieval; machine learning; feature engineering; multi-hidden layer neural network;

D O I：

10.1109/igarss.2019.8899792

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

In this paper, we propose a machine learning framework to conduct GNSS-R wind speed retrieval. While the conventional method tries to retrieve wind speed using a single scalar value, the proposed framework is capable of incorporating and employing more features such as DDM and incidence angle. The results show that the proposed framework outperforms the conventional retrieval method with a notable margin.

引用

页码：8707 / 8710

页数：4

共 50 条

[21] NEW APPROACH TO SEA SURFACE WIND RETRIEVAL FROM GNSS-R MEASUREMENTS [J].

Park, Hyuk ;

Valencia, Enric ;

Rodriguez-Alvarez, Nereida ;

Bosch-Lluis, Xavier ;

Ramos-Perez, Isaac ;

Camps, Adriano .

2011 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2011, :1469-1472

[22] Spaceborne GNSS-R combined with GNSS-IR for soil moisture retrieval [J].

Liu, Xu ;

Wang, Shiitai ;

Yin, Min ;

Wei, Jialin ;

Xu, Zengyang ;

Zhang, Xiaoyu ;

Lu, Zengyang .

ADVANCES IN SPACE RESEARCH, 2025, 76 (01) :32-45

[23] A GENERALIZED LINEAR OBSERVABLE FOR GNSS-R WIND SPEED RETRIEVALS OVER THE OCEAN [J].

Rodriguez-Alvarez, Nereida ;

Garrison, James L. .

2014 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2014, :3810-3813

[24] THE EMPIRICAL ORTHOGONAL FUNCTION THEORY AND SIMULATION RESEARCH FOR SPACEBORNE GNSS-R SEA SURFACE HIGH WIND SPEED RETRIEVAL [J].

Wu, J. M. ;

Chen, Y. L. ;

Guo, P. ;

Wang, X. Y. ;

Hu, X. G. ;

Wu, M. J. ;

Li, F. H. ;

Fu, N. F. .

2021 IEEE SPECIALIST MEETING ON REFLECTOMETRY USING GNSS AND OTHER SIGNALS OF OPPORTUNITY 2021 (GNSS+R 2021), 2021, :65-68

[25] Wind Speed Maping from the ISS Using GNSS-R? A Simulation Study [J].

Camps, A. ;

Park, H. ;

Alonso-Arroyo, A. .

2013 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2013, :382-385

[26] Machine learning-based global soil moisture estimation using GNSS-R [J].

Senyurek, Volkan ;

Lei, Fangni ;

Gurbuz, Ali C. ;

Kurum, Mehmet ;

Moorhead, Robert .

SOUTHEASTCON 2022, 2022, :434-435

[27] Improving GNSS-R Ocean Wind Speed Retrieval for the BF-1 Mission Using Satellite Platform Attitude Measurements [J].

Chen, Chenxin ;

Wang, Xiaoyu ;

Bian, Zhao ;

Wei, Haoyun ;

Fan, Dongdong ;

Bai, Zhaoguang .

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 :2121-2133

[28] Evaluation of Spaceborne GNSS-R Retrieved Ocean Surface Wind Speed with Multiple Datasets [J].

Dong, Zhounan ;

Jin, Shuanggen .

REMOTE SENSING, 2019, 11 (23)

[29] GNSS-R sea surface wind speed inversion based on BP neural network [J].

Gao H. ;

Bai Z. ;

Fan D. .

Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica, 2019, 40 (12)

[30] A New GNSS-R Altimetry Algorithm Based on Machine Learning Fusion Model and Feature Optimization to Improve the Precision of Sea Surface Height Retrieval [J].

Wang, Qiang ;

Zheng, Wei ;

Wu, Fan ;

Xu, Aigong ;

Zhu, Huizhong ;

Liu, Zongqiang .

FRONTIERS IN EARTH SCIENCE, 2021, 9

← 1 2 3 4 5 →