<br>基于深度学习的GNSS-R全球海面风速反演,IEEE Transactions on Geoscience and Remote Sensing

当前位置： X-MOL 学术 › IEEE Trans. Geosci. Remote Sens. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

基于深度学习的GNSS-R全球海面风速反演
IEEE Transactions on Geoscience and Remote Sensing ( IF 7.5 ) Pub Date : 2023-08-29 , DOI: 10.1109/tgrs.2023.3309690
Xiaoxu Liu ₁ , Weihua Bai ₁ , Guangyuan Tan ₁ , Feixiong Huang ₁ , Junming Xia ₁ , Cong Yin ₁ , Yueqiang Sun ₁ , Qifei Du ₁ , Xiangguang Meng ₁ , Congliang Liu ₁ , Peng Hu ₁

Affiliation

全球导航卫星系统反射测量（GNSS-R）是一种新兴的遥感观测技术，可以利用海面反射的卫星信号反演全球海面风速。该技术数据质量的提高和数据量的积累为构建跨学科的检索模型提供了数据支持。本文构建了一种基于深度学习的风速检索混合深度神经网络模型，可以接收整个延迟波形并进行特征挖掘，同时支持多种辅助特征输入并实现联合拟合。然后引入基于累积分布函数（CDF）匹配的偏差校正方法来减轻偏差，特别是在高风速下。我们通过设计特征消融分析来验证不同属性特征在风速检索中的贡献。对比分析了检索精度在时间维度上的波动变化和检索结果在空间上的分布。反演结果的均方根误差(RMSE)为1.486 m/s，在94.25%风速条件下可达1.399 m/s。经过基于CDF匹配的偏差修正后，高风速反演精度提高了7.19%。此外，该模型还具有良好的时间稳定性，可以在全球范围内再现大尺度风场，同时有效消除反演偏差，具有巨大的业务应用潜力。

"点击查看英文标题和摘要"

GNSS-R Global Sea Surface Wind Speed Retrieval Based on Deep Learning

Global navigation satellite system reflectometry (GNSS-R) is a burgeoning remote sensing observation technology that can retrieve global sea surface wind speeds using satellite signals reflected from the sea surface. The improvement of data quality and the accumulation of data volume of this technology provides data support for constructing interdisciplinary-based retrieval models. This article constructs a hybrid deep neural network model based on deep learning for wind speed retrieval, which can receive and perform feature mining on the entire delay waveform while simultaneously supporting multiple auxiliary features input and achieving joint fitting. Then a bias correction method based on cumulative distribution function (CDF) matching is introduced to mitigate bias, especially at high wind speeds. We verify the contribution of different attribute features in wind speed retrieval by designing a feature ablation analysis. The fluctuation variation of the retrieval accuracy in the time dimension and the retrieval results distribution in space are compared and analyzed. The root mean square error (RMSE) of retrieval results is 1.486 m/s and can reach 1.399 m/s under the 94.25% wind speed condition. After bias correction based on CDF matching, the retrieval accuracy at high wind speed is improved by 7.19%. Besides, this model also has good temporal stability and can reproduce large-scale wind fields while effectively mitigating retrieval bias on a global scale, showing great potential for operational applications.

更新日期：2023-08-29

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南