期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 57, 期 12, 页码 9756-9766出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2019.2929002
关键词
Advanced Scatterometer (ASCAT); cyclone global navigation satellite system (CYGNSS); deep learning; delay-Doppler map (DDM); GNSS-reflectometry (GNSS-R); multi-hidden layer neural network (MHL-NN); spaceborne remote sensing; wind speed retrieval
类别
资金
- Space Weather Technology, Research and Education Center (SWxTREK), University of Colorado at Boulder
- NASA [NNX15AT54G]
- NASA [803144, NNX15AT54G] Funding Source: Federal RePORTER
This paper applies a machine learning (ML) algorithm based on the multi-hidden layer neural network (MHL-NN) for ocean surface wind speed estimation using global navigation satellite system (GNSS) reflection measurements. Unlike conventional wind speed retrieval methods that often depend on limited scalar delay-Doppler map (DDM) observables, the proposed MHL-NN makes use of information captured by the entire DDM. Both simulated and real data sets are used to train and evaluate the performance of the MHL-NN and compare it to a conventional wind speed retrieval method and other prevailing ML algorithms. The results show that the MHL-NN algorithm outperforms the other methods in terms of the root mean square error (RMSE) and mean absolute percentage error (MAPE) of the wind speed estimation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据