Scholarlink

<p>The retrieval of sea surface wind speed is a key application of Global Navigation Satellite System-Reflectometry (GNSS-R). The continuous advancement of deep learning technologies has enabled the application of Convolutional Neural Network (CNN) models to retrieve sea surface wind speed from GNSS-R observables. However, the standard CNN models assign equal weight to all features, overlooking the more relevant ones, which reduces training efficiency and accuracy. To address this issue, this paper proposes a CNN model that incorporates the Squeeze-and-Excitation Network (SENet) attention mechanism, named CNN-SENet. The CNN-SENet model increases the weight for important features while suppressing the weight for less relevant ones, thereby improving accuracy and training efficiency. Results indicate that the CNN-SENet demonstrates a significant advantage in training efficiency over the standard CNN, reducing training time by nearly half. Additionally, the CNN-SENet model predicts the wind speeds in the range of 0–40&#xa0;m/s with a Root Mean Square Error (RMSE) of 1.29&#xa0;m/s and a coefficient of determination (<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="43020_2024_157_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="21" /> </InlineMediaObject> <EquationSource Format="TEX">\(R^{2}\)</EquationSource> <EquationSource Format="MATHML"><math> <msup> <mi>R</mi> <mn>2</mn> </msup> </math></EquationSource> </InlineEquation>) of 62.4%. It also outperforms both the standard CNN and the Geophysical Model Function (GMF), improving wind speed accuracy by 0.14&#xa0;m/s and 0.62&#xa0;m/s, respectively. Furthermore, the CNN-SENet model exhibits superior temporal generalization compared to the standard CNN.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CNN-SENet: a GNSS-R ocean wind speed retrieval model integrating CNN and SENet attention mechanism

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月18日

查看全文
  • Yimin Xia,
  • Dongliang Guan,
  • Zhiling Zhou

摘要

The retrieval of sea surface wind speed is a key application of Global Navigation Satellite System-Reflectometry (GNSS-R). The continuous advancement of deep learning technologies has enabled the application of Convolutional Neural Network (CNN) models to retrieve sea surface wind speed from GNSS-R observables. However, the standard CNN models assign equal weight to all features, overlooking the more relevant ones, which reduces training efficiency and accuracy. To address this issue, this paper proposes a CNN model that incorporates the Squeeze-and-Excitation Network (SENet) attention mechanism, named CNN-SENet. The CNN-SENet model increases the weight for important features while suppressing the weight for less relevant ones, thereby improving accuracy and training efficiency. Results indicate that the CNN-SENet demonstrates a significant advantage in training efficiency over the standard CNN, reducing training time by nearly half. Additionally, the CNN-SENet model predicts the wind speeds in the range of 0–40 m/s with a Root Mean Square Error (RMSE) of 1.29 m/s and a coefficient of determination ( \(R^{2}\) R 2 ) of 62.4%. It also outperforms both the standard CNN and the Geophysical Model Function (GMF), improving wind speed accuracy by 0.14 m/s and 0.62 m/s, respectively. Furthermore, the CNN-SENet model exhibits superior temporal generalization compared to the standard CNN.